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

    Neuronpedia

    INDEX
    Explanations

    references to classic works or elements in culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    earcher
    -0.76
    reon
    -0.72
     Simulator
    -0.70
    allah
    -0.68
    OTUS
    -0.66
    arching
    -0.66
    aughter
    -0.66
    lesh
    -0.65
    hani
    -0.65
    pta
    -0.63
    POSITIVE LOGITS
    arily
    0.85
    ised
    0.81
    ists
    0.81
     Revival
    0.80
    ist
    0.79
    ism
    0.76
    ized
    0.74
     Japanese
    0.74
     British
    0.73
    isation
    0.72
    Act Density 0.009%

    No Known Activations