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

    Neuronpedia

    INDEX
    Explanations

    references to physical strikes or impacts, particularly in a metaphorical or narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    534
    -0.17
    ipc
    -0.17
    ieg
    -0.15
    ForMember
    -0.15
     Holmes
    -0.15
    WARE
    -0.14
    _DROP
    -0.14
    Å¡ku
    -0.14
     dÄ±ÅŁÄ±
    -0.14
    'gc
    -0.14
    POSITIVE LOGITS
     punching
    0.19
     punched
    0.19
     punch
    0.19
     holes
    0.18
    ardon
    0.18
     fist
    0.16
    elog
    0.16
     punches
    0.16
    y
    0.16
    лан
    0.15
    Act Density 0.013%

    No Known Activations