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

    Neuronpedia

    INDEX
    Explanations

    words related to measurement, particularly indicating a quantity or size, such as 'half', 'three', 'eight', etc

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and measurements related to timeframes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PsyNetMessage
    -0.79
     tabs
    -0.69
    DERR
    -0.69
    çĶ°
    -0.67
    umbn
    -0.67
    berus
    -0.66
     IPM
    -0.65
    çīĪ
    -0.65
     Tuls
    -0.63
    auder
    -0.63
    POSITIVE LOGITS
    ccording
    1.06
    dozen
    1.02
    Lago
    0.91
    few
    0.90
    la
    0.88
    century
    0.85
    die
    0.81
    pill
    0.81
    compl
    0.81
    lot
    0.80
    Act Density 0.028%

    No Known Activations