Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of skepticism or criticism towards societal issues and figures, particularly related to racial dynamics and media representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by a verb implying deception or negativity

    np_acts-logits-general · gemini-2.0-flash

    questions and accusations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConverterFactory
    -0.61
    Tetapi
    -0.55
    abinieri
    -0.54
     Namun
    -0.54
    verzeichnis
    -0.53
     vanske
    -0.53
    IsMutable
    -0.52
     ating
    -0.52
    Nazionale
    -0.52
    HostException
    -0.52
    POSITIVE LOGITS
     blatantly
    0.92
     claiming
    0.85
     pretends
    0.78
     blaming
    0.78
    rungsseite
    0.76
     constantly
    0.74
     bewe
    0.74
     refuses
    0.74
     openly
    0.73
     lied
    0.72
    Act Density 0.541%

    No Known Activations