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

    Neuronpedia

    INDEX
    Explanations

    specific timestamps or durations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dep
    -0.16
    سÙĪ
    -0.15
     Bri
    -0.14
     fart
    -0.14
    ich
    -0.13
     resc
    -0.13
    èĶµ
    -0.13
    ied
    -0.13
     sw
    -0.13
     perman
    -0.13
    POSITIVE LOGITS
    rzy
    0.16
    irim
    0.16
    isses
    0.16
    strup
    0.15
    oppers
    0.15
    reator
    0.14
    بÙĬر
    0.14
    opsis
    0.13
    Guard
    0.13
    ynchronize
    0.13
    Act Density 0.223%

    No Known Activations