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

    Neuronpedia

    INDEX
    Explanations

    references to various frames and frameworks of understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :CGPoint
    -0.17
    rgan
    -0.17
    serie
    -0.17
    parm
    -0.15
    ä¼´
    -0.15
    room
    -0.15
    ivery
    -0.15
    onse
    -0.15
    istic
    -0.14
    ive
    -0.14
    POSITIVE LOGITS
    hift
    0.28
    less
    0.24
    ìĽĮíģ¬
    0.24
    buffers
    0.23
    æŀ¶
    0.20
    WORK
    0.18
    work
    0.18
    LESS
    0.18
    utas
    0.17
    413
    0.16
    Act Density 0.026%

    No Known Activations