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

    Neuronpedia

    INDEX
    Explanations

    expressive words and terms associated with challenges or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eoq
    -0.15
    ãģŁãģı
    -0.15
     Lands
    -0.14
    ÑĥÑĢÑģ
    -0.14
    itemap
    -0.14
    idade
    -0.13
    ÃŃsk
    -0.13
    (SE
    -0.13
    ĨĴ
    -0.13
    iosper
    -0.13
    POSITIVE LOGITS
     normal
    0.17
     actual
    0.16
     smaller
    0.16
    _actual
    0.16
     mere
    0.15
    ocities
    0.14
     traditional
    0.14
     small
    0.14
    obb
    0.14
     initial
    0.14
    Act Density 0.009%

    No Known Activations