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

    Neuronpedia

    INDEX
    Explanations

    words related to dissent, disagreement, and defection

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dissent and opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Parenthood
    -0.84
     ambul
    -0.65
     dams
    -0.65
    onut
    -0.65
    Iv
    -0.63
    estone
    -0.60
     Blocks
    -0.60
     stakes
    -0.60
     Mamm
    -0.58
     TT
    -0.58
    POSITIVE LOGITS
    arian
    0.82
    bryce
    0.80
    lust
    0.80
    aries
    0.78
    uous
    0.76
    edient
    0.74
    ctr
    0.73
    commun
    0.73
    adoes
    0.72
    arians
    0.71
    Act Density 0.130%

    No Known Activations