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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.56
    вік
    -0.55
     Feu
    -0.55
     pia
    -0.55
     trans
    -0.53
     Hein
    -0.53
     record
    -0.52
     Jacobsen
    -0.52
     $=$
    -0.52
    )
    -0.52
    POSITIVE LOGITS
     houſe
    0.92
     Houſe
    0.84
     purpoſe
    0.83
     whoſe
    0.80
     Pilate
    0.79
     myſelf
    0.79
     Athenians
    0.78
     abſ
    0.78
     uſe
    0.78
     deſt
    0.77
    Act Density 0.128%

    No Known Activations