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

    Neuronpedia

    INDEX
    Explanations

    specific names or identifiers associated with characters or entities in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ΣÏį
    -0.14
    δÏİ
    -0.14
    addir
    -0.14
     Baghd
    -0.14
    à¥Ŀ
    -0.13
    adÄĽ
    -0.13
    adla
    -0.12
    assi
    -0.12
    aggio
    -0.12
     Aura
    -0.12
    POSITIVE LOGITS
     nan
    0.71
    nan
    0.70
     Nan
    0.69
     NAN
    0.68
     Gan
    0.68
    han
    0.65
    lan
    0.63
     Lan
    0.63
    Han
    0.63
    gan
    0.62
    Act Density 0.575%

    No Known Activations