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

    Neuronpedia

    INDEX
    Explanations

    words associated with authority and influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.79
     betweenstory
    -0.66
     sexuelle
    -0.63
    Nuorodos
    -0.57
    autoreleasepool
    -0.54
     seksual
    -0.54
     Karsten
    -0.53
     esternos
    -0.53
    expandindo
    -0.52
    reportWebVitals
    -0.52
    POSITIVE LOGITS
    //
    0.75
     advantage
    0.69
    mtd
    0.67
     same
    0.63
    /*
    0.63
     exact
    0.62
     adequate
    0.62
     sufficient
    0.62
     necessary
    0.61
     stessi
    0.61
    Act Density 0.288%

    No Known Activations