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

    Neuronpedia

    INDEX
    Explanations

    words related to positions, associations, and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uce
    -0.15
    isd
    -0.15
    agon
    -0.15
    398
    -0.15
     operand
    -0.14
    Leod
    -0.14
    itten
    -0.14
     Mitar
    -0.14
     Ra
    -0.13
    çŃ
    -0.13
    POSITIVE LOGITS
    rut
    0.17
    Breadcrumb
    0.16
    alsa
    0.15
    anje
    0.15
    bern
    0.15
    ÅŁk
    0.14
     itemName
    0.14
    613
    0.14
     Alias
    0.14
    arnings
    0.14
    Act Density 0.008%

    No Known Activations