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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "overtake" or variations of it occur

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "overt" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesota
    -0.82
    UTION
    -0.80
     Crate
    -0.69
     Caps
    -0.66
    ulz
    -0.64
     Occupations
    -0.63
     SAR
    -0.62
     Trident
    -0.62
    GAN
    -0.61
     DRAG
    -0.61
    POSITIVE LOGITS
    uned
    0.97
    imes
    0.93
     overt
    0.90
    aken
    0.86
    empt
    0.86
    orial
    0.84
    orical
    0.82
    itled
    0.81
    aking
    0.80
    ener
    0.77
    Act Density 0.005%

    No Known Activations