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

    Neuronpedia

    INDEX
    Explanations

    mathematical and logical symbols or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     actionTypes
    -0.20
    dea
    -0.15
     اÙĦعظ
    -0.15
    iÄĻ
    -0.14
    lisi
    -0.14
    elib
    -0.14
    UFFER
    -0.14
    egrator
    -0.14
    wap
    -0.14
     âĹĦ
    -0.14
    POSITIVE LOGITS
    _bb
    0.15
    tro
    0.15
    NET
    0.14
     Bo
    0.14
     environmental
    0.14
    iali
    0.14
     hum
    0.13
    ãĥ³ãĥIJ
    0.13
    arse
    0.13
     Essence
    0.13
    Act Density 0.007%

    No Known Activations