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

    Neuronpedia

    INDEX
    Explanations

    singular references or mentions of entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.90
    Personendaten
    -0.80
    quelize
    -0.79
     Diſ
    -0.76
     myſelf
    -0.75
    ThroughAttribute
    -0.74
     Efq
    -0.74
    rsiniz
    -0.74
     obfer
    -0.74
    expandindo
    -0.72
    POSITIVE LOGITS
     of
    0.73
     kind
    0.66
     one
    0.66
     sort
    0.66
    one
    0.65
     like
    0.60
     One
    0.60
     sure
    0.58
     very
    0.57
     among
    0.56
    Act Density 0.020%

    No Known Activations