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

    Neuronpedia

    INDEX
    Explanations

    references to statistical or numerical data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bins
    -0.15
    ond
    -0.14
     sign
    -0.13
     f
    -0.13
    alog
    -0.13
    173
    -0.13
    opes
    -0.13
    amin
    -0.13
    aneous
    -0.13
    andro
    -0.13
    POSITIVE LOGITS
    ailles
    0.17
    aille
    0.16
    irth
    0.15
    ¶Į
    0.15
     sails
    0.15
     yOffset
    0.14
     nữa
    0.14
    곤
    0.14
    acen
    0.14
    letes
    0.14
    Act Density 0.007%

    No Known Activations