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

    Neuronpedia

    INDEX
    Explanations

    specific references to plans or project names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    اÙĨÙĩ
    -0.17
    idious
    -0.17
    alli
    -0.15
    dll
    -0.15
    nest
    -0.15
    anmar
    -0.15
    izable
    -0.15
    iams
    -0.15
    -light
    -0.15
    ibaba
    -0.15
    POSITIVE LOGITS
    etary
    0.32
    ets
    0.25
    ck
    0.23
    alto
    0.21
    escape
    0.21
     Parenthood
    0.20
    isphere
    0.19
    imet
    0.19
    ar
    0.19
    CK
    0.18
    Act Density 0.009%

    No Known Activations