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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "only."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.81
    RegressionTest
    -0.76
     itſelf
    -0.76
     reaſon
    -0.76
     didat
    -0.72
     cauſe
    -0.71
     neceff
    -0.70
     pouvoit
    -0.70
     tantum
    -0.69
     greateſt
    -0.67
    POSITIVE LOGITS
    __(/*!
    0.61
    endphp
    0.59
     Fah
    0.58
     useRef
    0.56
     gar
    0.55
     Donnelly
    0.54
     Ser
    0.53
    inda
    0.53
    ViewChild
    0.52
     useState
    0.52
    Act Density 0.013%

    No Known Activations