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

    Neuronpedia

    INDEX
    Explanations

    the use of mathematical operation indicators and formatting indicators in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Abitanti
    -0.86
    GEBURTSDATUM
    -0.78
    Massa
    -0.74
    хьтан
    -0.72
    ⓧ
    -0.72
    offsetof
    -0.69
     هيا
    -0.69
     noqa
    -0.68
     Mena
    -0.68
     alie
    -0.67
    POSITIVE LOGITS
    mathrm
    0.89
    '
    0.87
    setcounter
    0.82
    ’
    0.73
    URDAY
    0.65
    EEEEEEEE
    0.63
    çalves
    0.59
    󠁿
    0.59
    €™
    0.58
    schild
    0.58
    Act Density 0.025%

    No Known Activations