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

    Neuronpedia

    INDEX
    Explanations

    references to arXiv submissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.59
     consultato
    -0.55
    \}=
    -0.54
    jupiter
    -0.53
    )\}
    -0.53
     acceptez
    -0.53
    chenken
    -0.51
     ())
    -0.50
    )\}$
    -0.50
    LookAnd
    -0.50
    POSITIVE LOGITS
     wireType
    0.67
     الحره
    0.63
    LEGGI
    0.61
     actionMode
    0.60
    MMdd
    0.58
     chiffre
    0.58
     crossorigin
    0.56
     Shotgun
    0.54
    AlterField
    0.54
     '\\;'
    0.54
    Act Density 0.055%

    No Known Activations