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

    Neuronpedia

    INDEX
    Explanations

    functions related to data appending or managing lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.54
     B
    -0.54
    /
    -0.53
     Can
    -0.53
    -
    -0.53
     la
    -0.51
     U
    -0.50
     O
    -0.49
    Fig
    -0.49
     or
    -0.49
    POSITIVE LOGITS
     Monfieur
    1.26
     itſelf
    1.20
     themſelves
    1.20
     myſelf
    1.15
     Reſ
    1.07
     raiſ
    1.06
     Jefus
    1.04
     whoſe
    1.03
     himſelf
    1.03
     ainfi
    1.02
    Act Density 0.097%

    No Known Activations