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

    Neuronpedia

    INDEX
    Explanations

    phrases with the repetition of words

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mer
    -0.64
     gorilla
    -0.62
    leigh
    -0.58
     Worlds
    -0.58
     Photographer
    -0.57
     Courage
    -0.57
    {"
    -0.55
    amera
    -0.55
     Fighters
    -0.55
     Jav
    -0.54
    POSITIVE LOGITS
     beyond
    0.84
    over
    0.84
    above
    0.79
     above
    0.77
     over
    0.77
     parcel
    0.70
    OTT
    0.69
    rogen
    0.68
    âķIJ
    0.66
     Beyond
    0.66
    Act Density 0.023%

    No Known Activations