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

    Neuronpedia

    INDEX
    Explanations

    expressions that convey the existence or description of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    skyt
    -0.15
    رÙħ
    -0.14
     Kush
    -0.14
    od
    -0.14
     Kauf
    -0.14
     Ellis
    -0.14
    pak
    -0.14
    URY
    -0.14
    окол
    -0.13
    нÑıÑĤ
    -0.13
    POSITIVE LOGITS
    onte
    0.17
    onto
    0.15
    emes
    0.15
    ilon
    0.15
    reve
    0.14
    ADDE
    0.14
    Unsafe
    0.14
    ocache
    0.13
    inton
    0.13
    zure
    0.13
    Act Density 0.092%

    No Known Activations