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

    Neuronpedia

    INDEX
    Explanations

    numerical codes or signatures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific token

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.69
    heid
    -0.65
    manship
    -0.65
     Mechdragon
    -0.63
    folk
    -0.63
     Polo
    -0.62
     Loans
    -0.62
     Brach
    -0.61
    chel
    -0.61
    ORGE
    -0.60
    POSITIVE LOGITS
    adle
    1.34
    acker
    1.30
    ackers
    1.23
    acking
    1.18
    acked
    1.12
    ushed
    1.10
    anks
    1.07
    utch
    1.07
    umb
    1.06
    umble
    1.05
    Act Density 0.025%

    No Known Activations