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

    Neuronpedia

    INDEX
    Explanations

    phone numbers

    oai_token-act-pair · gpt-3.5-turbo

    phone numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bid
    -0.80
    lict
    -0.75
    uked
    -0.73
    agn
    -0.73
    unal
    -0.70
    alez
    -0.70
    oral
    -0.69
    acus
    -0.68
    alid
    -0.68
     refere
    -0.67
    POSITIVE LOGITS
     MHz
    0.92
     msec
    0.86
    Hz
    0.82
    989
    0.81
    ãĥ¼ãĥĨãĤ£
    0.80
    kHz
    0.77
    MHz
    0.77
    800
    0.77
     ILCS
    0.76
     kHz
    0.76
    Act Density 0.011%

    No Known Activations