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

    Neuronpedia

    INDEX
    Explanations

    references to specific brands, names, or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Alison
    -0.73
    yit
    -0.71
     Alison
    -0.71
     useDispatch
    -0.70
    SetOutput
    -0.66
    Portale
    -0.63
    yana
    -0.63
    y
    -0.62
    utton
    -0.62
    Nigel
    -0.60
    POSITIVE LOGITS
    es
    0.92
    nexo
    0.92
    BeginContext
    0.89
     ProtoMessage
    0.86
    ()]
    0.85
     оригіналу
    0.85
     referenties
    0.84
    ########.
    0.84
    terminator
    0.81
     Slab
    0.80
    Act Density 1.095%

    No Known Activations