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

    Neuronpedia

    INDEX
    Explanations

    key phrases or specific terms related to categorization or items in a list

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebek
    -0.19
     Swords
    -0.15
    crest
    -0.15
    fty
    -0.15
    ë¥
    -0.15
    LOAT
    -0.14
    μβ
    -0.14
    ymb
    -0.13
    νÏī
    -0.13
    abbo
    -0.13
    POSITIVE LOGITS
    оже
    0.16
    pton
    0.15
     Bien
    0.14
    undles
    0.14
    Argb
    0.14
     Duffy
    0.14
     Background
    0.14
    lean
    0.14
     sockets
    0.13
    stub
    0.13
    Act Density 0.057%

    No Known Activations