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

    Neuronpedia

    INDEX
    Explanations

    words related to government actions or policies

    oai_token-act-pair · gpt-3.5-turbo

    verbs that denote an action or process of alteration or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amar
    -0.93
    tu
    -0.73
    quartered
    -0.67
    pir
    -0.66
    oter
    -0.64
    itting
    -0.61
    anian
    -0.61
    spot
    -0.61
    imposed
    -0.61
    oat
    -0.60
    POSITIVE LOGITS
    ments
    0.91
    uate
    0.82
    enance
    0.81
    ably
    0.77
    Generic
    0.74
     yourselves
    0.74
     Yourself
    0.70
    ABLE
    0.69
     Clause
    0.69
    âĶĢâĶĢâĶĢâĶĢ
    0.69
    Act Density 0.088%

    No Known Activations