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

    Neuronpedia

    INDEX
    Explanations

    references to authority figures and hierarchical structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.72
     المعيارى
    -0.67
     ImportError
    -0.62
     complaining
    -0.59
     complaint
    -0.59
     HttpNotFound
    -0.58
     виправивши
    -0.58
     HasFactory
    -0.58
     مرئيه
    -0.57
    AndEndTag
    -0.55
    POSITIVE LOGITS
     coldly
    0.79
     stare
    0.76
     stared
    0.74
     staring
    0.70
     gaze
    0.70
     stood
    0.67
     cold
    0.64
     standing
    0.63
     calmly
    0.62
     sneered
    0.60
    Act Density 0.153%

    No Known Activations