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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating being off from a position or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orners
    -0.17
    iller
    -0.16
    خاÙĨÙĩ
    -0.15
    abinet
    -0.15
    opoulos
    -0.15
    ç¬
    -0.14
     Doub
    -0.14
    lar
    -0.14
    kbd
    -0.13
     Rak
    -0.13
    POSITIVE LOGITS
    kaar
    0.17
     Cobb
    0.15
    ifen
    0.15
    alli
    0.15
    ilty
    0.14
    erner
    0.14
    langs
    0.14
     indef
    0.14
    ACHE
    0.14
     -*
    0.14
    Act Density 0.007%

    No Known Activations