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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their emotional states or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fool
    -0.16
     Stre
    -0.14
     Fool
    -0.13
    atto
    -0.13
    874
    -0.12
    weise
    -0.12
    bout
    -0.12
    ange
    -0.12
    ly
    -0.12
     itself
    -0.12
    POSITIVE LOGITS
    -même
    0.17
    alic
    0.16
    'll
    0.16
    pherd
    0.15
    ’ll
    0.15
    /she
    0.14
    /us
    0.14
    strcasecmp
    0.14
    inous
    0.13
    ela
    0.13
    Act Density 0.963%

    No Known Activations