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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating specificity or uniqueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abet
    -0.15
    Å
    -0.14
    spar
    -0.13
     (
    -0.13
    utton
    -0.13
    urt
    -0.13
    offs
    -0.13
    lik
    -0.13
    ries
    -0.13
     Coastal
    -0.12
    POSITIVE LOGITS
    ilden
    0.16
     впол
    0.14
     fetisch
    0.14
    okud
    0.14
     verir
    0.14
    abouts
    0.14
     Beled
    0.14
     à¹Ĩ
    0.14
    ertino
    0.14
    าà¸ĵ
    0.14
    Act Density 0.001%

    No Known Activations