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

    Neuronpedia

    INDEX
    Explanations

    references to magic and magical themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GEBURTS
    -0.55
     volontaire
    -0.54
     utafitiHapana
    -0.53
    ROUGH
    -0.52
    ThroughAttribute
    -0.52
    iths
    -0.51
    vaiz
    -0.51
    PreferredItem
    -0.51
    ardless
    -0.50
    proud
    -0.50
    POSITIVE LOGITS
    aarrggbb
    0.71
     wand
    0.71
     tricks
    0.70
     realist
    0.69
     trick
    0.68
     ModelExpression
    0.65
     potion
    0.64
    🪄
    0.64
     words
    0.64
     powers
    0.63
    Act Density 0.163%

    No Known Activations