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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing excessive or negative sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ®Ĭ
    -0.15
    acht
    -0.14
    ade
    -0.14
    chn
    -0.14
     Howe
    -0.14
     RectTransform
    -0.14
    ullo
    -0.14
     strom
    -0.14
    vet
    -0.13
    acad
    -0.13
    POSITIVE LOGITS
    eyh
    0.15
    ahlen
    0.15
    oningen
    0.14
     SetProperty
    0.14
    ÑĩÑĸ
    0.14
    yg
    0.14
    ecimal
    0.14
     onCreateViewHolder
    0.14
    weg
    0.14
     Blo
    0.14
    Act Density 0.010%

    No Known Activations