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

    Neuronpedia

    INDEX
    Explanations

    words that indicate a significant degree of impact or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     large
    -0.16
    омен
    -0.15
    -sized
    -0.14
    -large
    -0.14
     Famous
    -0.14
    enger
    -0.14
     Nä
    -0.14
     strong
    -0.14
     blindness
    -0.14
     Meng
    -0.14
    POSITIVE LOGITS
    asca
    0.18
     outnumber
    0.16
     denn
    0.15
    .masks
    0.15
    μι
    0.14
    lac
    0.14
    unsch
    0.14
    udo
    0.14
    bes
    0.14
    .vs
    0.14
    Act Density 0.060%

    No Known Activations