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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal choices or preferences

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases related to desires, needs, and intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipel
    -0.80
    hoe
    -0.73
     Lines
    -0.69
    ioxide
    -0.69
     Planes
    -0.68
    oxide
    -0.67
    lang
    -0.65
    uterte
    -0.63
    hov
    -0.63
    igl
    -0.63
    POSITIVE LOGITS
     altru
    0.70
     reciproc
    0.67
     justifies
    0.66
     bribes
    0.66
     forgiveness
    0.66
     reperto
    0.64
    aceae
    0.64
    buy
    0.63
     barg
    0.62
     allowances
    0.60
    Act Density 0.602%

    No Known Activations