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

    Neuronpedia

    INDEX
    Explanations

    events that evoke strong reactions or significant actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tics
    -0.07
     Äĩe
    -0.07
    istrovstvÃŃ
    -0.07
    IIIK
    -0.07
    ãģłãģ£ãģ¦
    -0.07
     gonna
    -0.07
    _cmos
    -0.07
     olmadan
    -0.07
    asaki
    -0.07
    atÃŃm
    -0.07
    POSITIVE LOGITS
     earlier
    0.09
     became
    0.08
     gave
    0.08
     took
    0.07
     elsewhere
    0.07
     failed
    0.07
     saw
    0.06
    Earlier
    0.06
     leave
    0.06
     began
    0.06
    Act Density 0.055%

    No Known Activations