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

    Neuronpedia

    INDEX
    Explanations

    mentions of process-related keywords

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    legged
    -0.72
     Haram
    -0.71
    glers
    -0.70
    pees
    -0.67
    gged
    -0.66
    aez
    -0.65
    him
    -0.65
    pee
    -0.64
    fed
    -0.63
    lar
    -0.61
    POSITIVE LOGITS
    ional
    1.24
    ions
    1.07
    ivity
    0.99
    ors
    0.93
    ivism
    0.84
    Memory
    0.82
    ioned
    0.81
    IONS
    0.78
    mable
    0.76
    icity
    0.76
    Act Density 0.017%

    No Known Activations