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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "poles"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Boles"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SUP
    -0.67
    EXP
    -0.66
    Flight
    -0.63
     CARD
    -0.62
    Export
    -0.60
    Reply
    -0.60
    ANC
    -0.59
    LESS
    -0.57
    ARR
    -0.57
    Boost
    -0.56
    POSITIVE LOGITS
    oles
    1.23
    ktop
    0.98
    ole
    0.95
    pora
    0.93
    terness
    0.90
    hift
    0.88
    cules
    0.88
    ippi
    0.87
    nikov
    0.87
    cot
    0.85
    Act Density 0.009%

    No Known Activations