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

    Neuronpedia

    INDEX
    Explanations

    mentions of location

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and the definite article "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Solitaire
    -0.65
     Mb
    -0.63
    SPONSORED
    -0.60
     Plum
    -0.59
    hower
    -0.59
     Penal
    -0.58
     prod
    -0.58
     Lol
    -0.57
    ONEY
    -0.57
     Lady
    -0.56
    POSITIVE LOGITS
    alog
    0.92
    vised
    0.82
    lihood
    0.77
    alogue
    0.76
    quartered
    0.74
    tenance
    0.73
    \\\\\\\\
    0.73
    xiety
    0.72
    focused
    0.72
    etheless
    0.72
    Act Density 0.104%

    No Known Activations