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

    Neuronpedia

    INDEX
    Explanations

    technical specifications like dimensions, weights, and measurements

    oai_token-act-pair · gpt-3.5-turbo

    numeric specifications and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nik
    -0.86
    oppers
    -0.84
    zik
    -0.77
    orsi
    -0.76
    acci
    -0.75
    nesday
    -0.73
     scrut
    -0.71
    atars
    -0.71
    isphere
    -0.70
    icip
    -0.70
    POSITIVE LOGITS
    125
    0.75
     hrs
    0.71
    75
    0.70
     1280
    0.70
     /
    0.70
     Starts
    0.70
    192
    0.70
    67
    0.68
    264
    0.68
     660
    0.67
    Act Density 0.220%

    No Known Activations