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

    Neuronpedia

    INDEX
    Explanations

    phrases related to checking or verifying something

    oai_token-act-pair · gpt-3.5-turbo

    uses of the word "check" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hots
    -0.77
    ufact
    -0.73
    Church
    -0.73
    brance
    -0.69
     ç¥ŀ
    -0.69
    bold
    -0.68
    SAY
    -0.67
    chal
    -0.66
    BLE
    -0.65
    ña
    -0.63
    POSITIVE LOGITS
    etts
    0.88
    ysis
    0.85
    boxes
    0.80
    ipers
    0.78
    enhagen
    0.76
    lists
    0.76
    ers
    0.73
    ups
    0.72
    opes
    0.71
    mate
    0.69
    Act Density 0.020%

    No Known Activations