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

    Neuronpedia

    INDEX
    Explanations

    instances of significant actions, concepts, or descriptors related to enforcement, decision-making, and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ispers
    -0.16
     Esp
    -0.15
    illo
    -0.15
    obl
    -0.15
     Hi
    -0.14
    ANGLE
    -0.14
    oru
    -0.14
    .struct
    -0.13
    ãĤ«ãĥĨãĤ´ãĥª
    -0.13
    lyn
    -0.13
    POSITIVE LOGITS
    allee
    0.17
     occasional
    0.15
    olini
    0.15
    _SECURE
    0.15
     barg
    0.14
     unless
    0.14
    63
    0.14
    asher
    0.13
    @email
    0.13
    vertime
    0.13
    Act Density 0.009%

    No Known Activations