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

    Neuronpedia

    INDEX
    Explanations

    phone numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and associated values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scenery
    -0.67
     immedi
    -0.62
     tongues
    -0.58
     ale
    -0.57
     Abbey
    -0.57
     bridges
    -0.57
     kne
    -0.57
    5
    -0.56
     Spiel
    -0.56
     lightly
    -0.56
    POSITIVE LOGITS
    128
    1.09
    157
    1.07
    158
    1.07
    194
    1.07
    127
    1.06
    199
    1.06
    148
    1.05
    299
    1.05
    196
    1.05
    198
    1.05
    Act Density 0.106%

    No Known Activations