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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "part" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ly
    -0.36
    LY
    -0.21
    hound
    -0.17
    lü
    -0.17
    eous
    -0.17
    erator
    -0.16
    ÙģØ©
    -0.16
    hammer
    -0.16
    whelming
    -0.16
    اÙĦÙī
    -0.16
    POSITIVE LOGITS
    isans
    0.35
    cip
    0.34
    ake
    0.29
    aking
    0.28
    ook
    0.27
    ipation
    0.26
    -time
    0.25
    iceps
    0.24
    cular
    0.24
    ip
    0.24
    Act Density 0.025%

    No Known Activations