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

    Neuronpedia

    INDEX
    Explanations

    terms related to adjustability or customizable features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eward
    -0.15
    raki
    -0.15
    idal
    -0.15
     Ñģеб
    -0.15
    ertiary
    -0.15
    uffix
    -0.14
    imet
    -0.14
    icare
    -0.14
    iversit
    -0.14
     fountain
    -0.14
    POSITIVE LOGITS
    gart
    0.18
    éĩı
    0.15
    tap
    0.15
    ÑĨий
    0.14
    840
    0.14
    andra
    0.14
    igious
    0.14
     loose
    0.14
    _APPEND
    0.14
     Loose
    0.14
    Act Density 0.006%

    No Known Activations