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

    Neuronpedia

    INDEX
    Explanations

    indefinite articles followed by various nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    faces
    -0.16
     unchecked
    -0.16
    ivos
    -0.16
    _dropout
    -0.15
    OrElse
    -0.14
    ponent
    -0.13
     bang
    -0.13
    िब
    -0.13
    cko
    -0.13
    fur
    -0.13
    POSITIVE LOGITS
     cue
    0.20
     look
    0.19
     oath
    0.18
     Cue
    0.18
     closer
    0.17
     stab
    0.17
     liking
    0.17
    aliz
    0.17
     det
    0.16
    dete
    0.16
    Act Density 0.027%

    No Known Activations