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

    Neuronpedia

    INDEX
    Explanations

    references to academic research and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -0.79
     '\\;'
    -0.75
    Попис
    -0.71
    ￡
    -0.71
    httphttps
    -0.70
    IntoConstraints
    -0.70
    ArrowToggle
    -0.68
     الحره
    -0.67
    writeFieldEnd
    -0.66
    kháu
    -0.66
    POSITIVE LOGITS
    ismer
    0.52
    agerie
    0.48
    vangen
    0.46
     top
    0.45
     STEM
    0.43
    viol
    0.43
     sam
    0.43
    ai
    0.42
    implode
    0.41
     złoż
    0.41
    Act Density 0.468%

    No Known Activations