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

    Neuronpedia

    INDEX
    Explanations

    indicators of personal experience or opinions related to societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ком
    -0.50
    naio
    -0.49
    iele
    -0.48
    urate
    -0.47
     enf
    -0.47
    antiation
    -0.46
     Her
    -0.46
    quing
    -0.44
    ながらも
    -0.44
    curi
    -0.44
    POSITIVE LOGITS
     gotta
    0.84
    GEBURTSDATUM
    0.83
     prolly
    0.82
    LookAnd
    0.81
     wouldn
    0.79
     gonna
    0.78
     loves
    0.77
     really
    0.77
     won
    0.76
    getMenuInflater
    0.76
    Act Density 0.472%

    No Known Activations