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

    Neuronpedia

    INDEX
    Explanations

    discourse surrounding public speculation and controversy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.97
     myſelf
    -0.90
     Jefus
    -0.90
     pleaſure
    -0.88
     itſelf
    -0.86
     utafitiHapana
    -0.85
    ſelf
    -0.84
     للاسماء
    -0.83
     himſelf
    -0.83
     purpoſe
    -0.81
    POSITIVE LOGITS
     reactions
    0.61
     backlash
    0.52
     rumours
    0.49
     rumors
    0.49
     rumores
    0.49
    reactions
    0.47
     commentators
    0.46
    portál
    0.46
     whispers
    0.46
     Reactions
    0.46
    Act Density 0.350%

    No Known Activations