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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating strong certainty or definitive statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    romatic
    -0.15
    eniz
    -0.14
    iens
    -0.14
    cker
    -0.14
    cka
    -0.13
     Inherits
    -0.13
     hers
    -0.13
    ABCDEFG
    -0.13
    ÑģÑĭ
    -0.13
    heimer
    -0.13
    POSITIVE LOGITS
    aze
    0.15
    -regexp
    0.15
    nÃŃk
    0.15
    odzi
    0.14
     Reactive
    0.14
    oting
    0.14
    pei
    0.14
    nout
    0.14
    asso
    0.13
    ableView
    0.13
    Act Density 0.044%

    No Known Activations