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

    Neuronpedia

    INDEX
    Explanations

    portions of text that illustrate definitions or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.16
     purpoſe
    -1.10
    ThroughAttribute
    -1.09
     ſtate
    -1.03
     raiſ
    -1.02
     ſever
    -1.00
     Monfieur
    -0.99
     pleaſure
    -0.98
     uſed
    -0.97
     themſelves
    -0.97
    POSITIVE LOGITS
     is
    1.72
     è
    1.41
     είναι
    1.23
     adalah
    1.16
     was
    1.15
     là
    1.14
     es
    1.10
    ίναι
    1.10
     ist
    1.09
     are
    1.08
    Act Density 0.018%

    No Known Activations