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

    Neuronpedia

    INDEX
    Explanations

    words related to conflicts, confrontations, and significant challenges

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant societal outcomes and conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scant
    -0.57
    Lic
    -0.55
    guyen
    -0.55
    athi
    -0.54
     SHOW
    -0.53
     Liv
    -0.52
     bikini
    -0.52
    artment
    -0.52
     diaper
    -0.52
     ISO
    -0.51
    POSITIVE LOGITS
    thood
    1.03
     someday
    0.82
    livion
    0.75
    anship
    0.74
     unless
    0.73
     tomorrow
    0.73
    ternity
    0.73
     purposes
    0.68
    matically
    0.67
     ASAP
    0.66
    Act Density 0.351%

    No Known Activations