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
    lict
    -0.75
    bid
    -0.73
    actor
    -0.70
    oral
    -0.69
    acco
    -0.69
    alez
    -0.68
    agn
    -0.67
    oles
    -0.66
    unal
    -0.66
    acus
    -0.65
    POSITIVE LOGITS
     MHz
    0.84
    989
    0.84
    ãĥ¼ãĥĨãĤ£
    0.79
     Meadow
    0.79
     msec
    0.79
    eenth
    0.75
     IU
    0.73
    MHz
    0.71
    scl
    0.71
    ãĥ¼ãĥ«
    0.69
    Act Density 0.021%

    No Known Activations