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

    Neuronpedia

    INDEX
    Explanations

    emphasis and formatting tags within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nze
    -0.17
    erre
    -0.16
    gratis
    -0.15
    ston
    -0.15
    atoes
    -0.15
    WebService
    -0.15
    agg
    -0.14
    lopen
    -0.14
    unya
    -0.14
    andles
    -0.14
    POSITIVE LOGITS
    aly
    0.17
     McN
    0.15
    iÃŁ
    0.14
     REGARD
    0.14
    CLUDING
    0.13
    viso
    0.13
    ally
    0.13
    ((__
    0.13
    aru
    0.13
    -speaking
    0.13
    Act Density 0.013%

    No Known Activations