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

    Neuronpedia

    INDEX
    Explanations

    words related to types of observations and measurements in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TextAppearance
    -0.34
    evt
    -0.34
    BeginContext
    -0.34
    rich
    -0.32
    อัน
    -0.32
    beza
    -0.31
    ever
    -0.31
    bidi
    -0.31
    های
    -0.31
     GIPHY
    -0.30
    POSITIVE LOGITS
    tte
    0.58
    이션
    0.57
    lle
    0.57
    ctomy
    0.57
    tti
    0.52
    aux
    0.52
    urs
    0.52
    lled
    0.52
    lli
    0.52
    tt
    0.52
    Act Density 0.300%

    No Known Activations