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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discussions about character motivations and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     HasFactory
    -0.93
    رشف
    -0.91
     MainAxisSize
    -0.90
    AnchorStyles
    -0.90
     utafitiHapana
    -0.85
    GEBURTSDATUM
    -0.79
    Composable
    -0.79
    parsedMessage
    -0.77
    afficheront
    -0.75
    yntaxException
    -0.74
    POSITIVE LOGITS
     what
    0.37
     lots
    0.33
     mucha
    0.32
     nothing
    0.32
     doing
    0.31
     because
    0.31
     ledit
    0.30
     ciò
    0.30
    mentioned
    0.30
     many
    0.29
    Act Density 2.054%

    No Known Activations