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

    Neuronpedia

    INDEX
    Explanations

    references to specific scientific studies or articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ExtendWith
    -0.57
    fromnode
    -0.57
    UTERS
    -0.57
     SwitchCompat
    -0.55
     autorytatywna
    -0.54
    zzar
    -0.52
     OMITBAD
    -0.50
    OGND
    -0.50
     aktive
    -0.50
    ніципалі
    -0.50
    POSITIVE LOGITS
    Zeneca
    0.63
     sportback
    0.59
    phous
    0.57
    ัติ
    0.56
    readObject
    0.55
     Paglinawan
    0.55
    baijan
    0.54
     hưởng
    0.54
    żeń
    0.53
    醐
    0.53
    Act Density 0.511%

    No Known Activations