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

    Neuronpedia

    INDEX
    Explanations

    underscore-prefixed identifiers or variable names in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.61
     Hopf
    -0.53
     conmigo
    -0.51
     italienne
    -0.50
     sehari
    -0.50
     Philist
    -0.49
     cardiaque
    -0.49
     Obr
    -0.49
     Ungarn
    -0.48
     presidencia
    -0.48
    POSITIVE LOGITS
    ########.
    0.84
    "]/
    0.82
     مُعرِّف
    0.79
    IBOutlet
    0.77
    +
    0.76
    Gön
    0.75
    ".
    0.74
    [])
    0.73
    _
    0.73
    --
    0.73
    Act Density 0.231%

    No Known Activations