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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical characteristics or locations

    oai_token-act-pair · gpt-3.5-turbo

    contrasting descriptions of characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âķIJâķIJ
    -0.66
     GOODMAN
    -0.60
    perate
    -0.54
     Insight
    -0.53
     Reach
    -0.51
     )]
    -0.51
     sidx
    -0.51
    versely
    -0.51
    liest
    -0.50
    staking
    -0.50
    POSITIVE LOGITS
     outwe
    0.67
    smanship
    0.63
     imaginable
    0.62
    isms
    0.61
    ãĥ³ãĤ¸
    0.57
     awaits
    0.57
    ahime
    0.55
     creations
    0.54
    unia
    0.53
    ãĤ¤ãĥĪ
    0.53
    Act Density 1.589%

    No Known Activations