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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to named entities or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñĥже
    -0.16
    füg
    -0.15
     Garn
    -0.14
    оÑģÑĥд
    -0.14
    lod
    -0.14
    isme
    -0.13
    another
    -0.13
    .Aggressive
    -0.13
    udos
    -0.13
    Narrated
    -0.13
    POSITIVE LOGITS
     '
    0.23
     "
    0.23
     simply
    0.21
     ‘
    0.20
     “
    0.20
     «
    0.19
     simplement
    0.18
     ``
    0.16
     \"
    0.15
     `
    0.15
    Act Density 0.082%

    No Known Activations