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

    Neuronpedia

    INDEX
    Explanations

    references to evaluations or judgments related to people or societal constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hobo
    -0.55
    Portale
    -0.55
    essentiel
    -0.54
    Gweler
    -0.53
     eventual
    -0.52
    ığım
    -0.52
     Nigerian
    -0.51
    ربية
    -0.51
     conventional
    -0.51
     GARDEN
    -0.51
    POSITIVE LOGITS
     گیا
    0.55
    ionage
    0.54
    FileVersion
    0.53
    вся
    0.49
     kaybet
    0.48
    puri
    0.48
     createSlice
    0.48
    ThroughAttribute
    0.46
    SequentialGroup
    0.46
     JUGA
    0.46
    Act Density 0.024%

    No Known Activations