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

    Neuronpedia

    INDEX
    Explanations

    numbers related to quantities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of commas in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hitman
    -0.63
     beauty
    -0.62
    enhagen
    -0.60
     FTA
    -0.59
     Ludwig
    -0.58
     dissertation
    -0.58
     bos
    -0.58
     reconciliation
    -0.57
    lication
    -0.56
     entitlement
    -0.56
    POSITIVE LOGITS
    000
    1.46
    800
    1.22
    700
    1.19
    600
    1.14
    500
    1.11
    400
    1.04
    300
    1.04
    200
    1.02
    900
    0.98
    08
    0.97
    Act Density 0.118%

    No Known Activations