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

    Neuronpedia

    INDEX
    Explanations

    technical specifications related to computer hardware

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and measurements related to specifications or data in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eding
    -0.69
    eded
    -0.64
    artisan
    -0.64
    ception
    -0.61
    cles
    -0.61
    emaker
    -0.60
    quet
    -0.60
    waves
    -0.59
    achi
    -0.59
    ceptive
    -0.58
    POSITIVE LOGITS
    wagen
    0.93
     ILCS
    0.92
    marked
    0.88
    AMS
    0.81
    mAh
    0.74
    mere
    0.72
    ution
    0.70
    aml
    0.70
    401
    0.69
    315
    0.67
    Act Density 0.082%

    No Known Activations