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

    Neuronpedia

    INDEX
    Explanations

    instances of chaotic or uncontrolled behavior, especially in a literal or metaphorical sense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yoda
    -0.58
     createState
    -0.55
     olmak
    -0.55
    omiya
    -0.54
     виправивши
    -0.51
     đôi
    -0.49
    uerre
    -0.48
    Humph
    -0.47
     taşı
    -0.47
     afstand
    -0.47
    POSITIVE LOGITS
     burst
    0.92
     exuber
    0.92
     uncontrolled
    0.91
     unleashed
    0.89
     rampage
    0.89
     frenzy
    0.88
     madly
    0.85
     uncontrol
    0.83
     uncontrollable
    0.83
     raging
    0.83
    Act Density 0.378%

    No Known Activations