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

    Neuronpedia

    INDEX
    Explanations

    instances of special characters or formatting cues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.17
     pleaſure
    -0.99
     Efq
    -0.99
     poffe
    -0.95
     poffible
    -0.95
     ExecuteAsync
    -0.95
     cauſe
    -0.93
     myſelf
    -0.91
     houſe
    -0.91
     himſelf
    -0.88
    POSITIVE LOGITS
     “
    0.68
     ‘
    0.66
    “
    0.65
    ::<
    0.59
    {
    0.59
    "=>"
    0.59
     Lu
    0.56
    ‘
    0.55
     Y
    0.55
    ={`${
    0.55
    Act Density 0.052%

    No Known Activations