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

    Neuronpedia

    INDEX
    Explanations

    negating phrases or expressions indicating exceptions or criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orks
    -0.15
    fffffff
    -0.15
    ustos
    -0.15
    ÑĢÑĸд
    -0.14
    amin
    -0.14
    ÙĪÙĦÛĮ
    -0.14
     лиÑģÑĤоп
    -0.14
    .lu
    -0.14
    æ£Ĵ
    -0.14
     Dabei
    -0.14
    POSITIVE LOGITS
     mo
    0.17
    ANGE
    0.16
    anje
    0.16
    /npm
    0.15
    omba
    0.15
     MOT
    0.15
     indeed
    0.15
     æģ
    0.14
     dry
    0.14
     twilight
    0.14
    Act Density 0.020%

    No Known Activations