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

    Neuronpedia

    INDEX
    Explanations

    phrases related to seeking information or solutions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the search for news and information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.79
    Ö¼
    -0.72
    ographed
    -0.69
     notably
    -0.66
     Think
    -0.66
     Notting
    -0.65
     boasted
    -0.64
     testified
    -0.63
     unanimously
    -0.62
     pressured
    -0.61
    POSITIVE LOGITS
    hower
    0.81
     elusive
    0.79
     reinforcements
    0.76
    next
    0.70
    fficiency
    0.70
     imminent
    0.69
    ById
    0.68
     distraction
    0.67
     reasons
    0.67
     inspiration
    0.66
    Act Density 0.292%

    No Known Activations