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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their associated symbols, indicating a focus on data representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    momix
    -0.74
    hwar
    -0.67
     NgModule
    -0.63
    Wart
    -0.63
    moveToFirst
    -0.63
    twimg
    -0.59
    áli
    -0.59
    lith
    -0.59
    ךְ
    -0.59
     ponte
    -0.59
    POSITIVE LOGITS
     poffible
    0.76
     iſt
    0.73
    Kaynakça
    0.70
     Eighty
    0.69
     Ninety
    0.69
     eighty
    0.69
     (;;)
    0.69
     Eſ
    0.67
    팎
    0.67
     ninety
    0.67
    Act Density 0.366%

    No Known Activations