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

    Neuronpedia

    INDEX
    Explanations

    bracketed sections or square brackets in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ssue
    -0.15
    aneous
    -0.15
    l
    -0.14
    ati
    -0.14
    ufen
    -0.13
     Äijá»ķi
    -0.13
    lah
    -0.13
    åį´
    -0.13
    ssel
    -0.13
    ัล
    -0.13
    POSITIVE LOGITS
    +]
    0.17
    urette
    0.16
    getc
    0.15
    incinn
    0.15
    grave
    0.14
    üçük
    0.14
    ¢åįķ
    0.14
     nhau
    0.14
    ameda
    0.14
    âĸį
    0.14
    Act Density 0.117%

    No Known Activations