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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    phrases or constructions that imply possession or affiliation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivation
    -0.84
    é¾
    -0.74
    sth
    -0.74
    potion
    -0.74
    mod
    -0.72
    meal
    -0.70
    ibe
    -0.68
    factor
    -0.68
    isine
    -0.68
    andum
    -0.66
    POSITIVE LOGITS
     various
    1.27
     varying
    1.03
     both
    1.02
     numerous
    1.01
     several
    0.97
     departments
    0.97
     different
    0.94
     innumerable
    0.93
     cities
    0.91
     dozens
    0.91
    Act Density 0.612%

    No Known Activations