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

    Neuronpedia

    INDEX
    Explanations

    references to specific actions or instructions related to tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilt
    -0.18
     عاش
    -0.15
    egis
    -0.15
    vinc
    -0.14
    noinspection
    -0.14
    unting
    -0.14
    éné
    -0.14
    ensus
    -0.14
    endors
    -0.14
    enda
    -0.14
    POSITIVE LOGITS
    ano
    0.33
    ana
    0.30
    ано
    0.28
    anos
    0.28
    ani
    0.27
    ann
    0.27
    anie
    0.27
    ана
    0.26
    ane
    0.26
    ANO
    0.25
    Act Density 0.024%

    No Known Activations