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

    Neuronpedia

    INDEX
    Explanations

    elements related to childlike or playful imagery and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leban
    -0.16
    пÑĢа
    -0.15
    arkan
    -0.15
    agit
    -0.14
    ethyst
    -0.14
     dodge
    -0.14
     Neptune
    -0.14
    ukan
    -0.14
    ISIBLE
    -0.14
    _VISIBLE
    -0.14
    POSITIVE LOGITS
     Po
    0.38
     Winn
    0.37
     Mil
    0.32
    Po
    0.30
     Christopher
    0.29
     Hundred
    0.27
    Mil
    0.27
     honey
    0.25
     po
    0.25
     Pig
    0.25
    Act Density 0.001%

    No Known Activations