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

    Neuronpedia

    INDEX
    Explanations

    programming or code-related keywords and their structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.58
    ,
    -0.47
    -
    -0.46
     –
    -0.42
     -
    -0.41
    (
    -0.40
     /
    -0.38
     m
    -0.38
     ba
    -0.37
    .
    -0.37
    POSITIVE LOGITS
     Monfieur
    1.02
    StoryboardSegue
    1.00
    rungsseite
    0.99
     Efq
    0.97
    saraba
    0.96
     doubtnut
    0.93
     تانيه
    0.92
     lenker
    0.91
     myſelf
    0.91
     contextLoads
    0.90
    Act Density 0.038%

    No Known Activations