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

    Neuronpedia

    INDEX
    Explanations

    references to academic papers and their details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yar
    -0.18
    y
    -0.15
    yg
    -0.15
    yun
    -0.15
    inel
    -0.15
    uos
    -0.15
    yu
    -0.15
    entifier
    -0.15
    ot
    -0.15
    yd
    -0.14
    POSITIVE LOGITS
    clip
    0.18
    ÚĨÛĮ
    0.17
    centage
    0.16
    theid
    0.15
    UDA
    0.15
    ãģ°
    0.15
    /board
    0.14
     Pant
    0.14
    ież
    0.14
    /books
    0.14
    Act Density 0.028%

    No Known Activations