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

    Neuronpedia

    INDEX
    Explanations

    words related to requirements or necessities

    oai_token-act-pair · gpt-3.5-turbo

    obligatory actions or structures associated with rules and guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.55
    ividual
    -0.54
    Eth
    -0.53
    pherd
    -0.53
    $.
    -0.52
    arter
    -0.52
    olicy
    -0.52
    ierre
    -0.51
    '."
    -0.50
    erenn
    -0.50
    POSITIVE LOGITS
    pires
    0.54
    SL
    0.53
    auna
    0.49
    moon
    0.49
     belonged
    0.48
    natureconservancy
    0.47
     belongs
    0.47
    ģĸ
    0.47
     foreskin
    0.46
     resides
    0.46
    Act Density 0.252%

    No Known Activations