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

    Neuronpedia

    INDEX
    Explanations

    sequences of underscores and non-standard formatting markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    3
    -0.58
    .
    -0.58
    1
    -0.57
    /
    -0.56
    The
    -0.55
    4
    -0.55
    2
    -0.54
     
    -0.54
    5
    -0.54
    0
    -0.51
    POSITIVE LOGITS
    ьаж
    0.95
    protoimpl
    0.95
     myſelf
    0.91
    UserScript
    0.89
     Савезне
    0.88
     pleaſure
    0.87
    談社
    0.86
    featureID
    0.86
     itſelf
    0.84
     Lightboxes
    0.84
    Act Density 0.272%

    No Known Activations