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

    Neuronpedia

    INDEX
    Explanations

    phrases related to future intentions or possibilities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to potential and prospective scenarios or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anguage
    -0.88
    esthesia
    -0.76
    urgy
    -0.75
    thora
    -0.73
    ossession
    -0.73
    ologue
    -0.70
    tein
    -0.69
    lain
    -0.69
    ollen
    -0.69
    illance
    -0.66
    POSITIVE LOGITS
     buyers
    1.20
     recipients
    1.17
     investors
    1.13
     entrants
    1.12
     purch
    1.11
     subscribers
    1.09
     travelers
    1.09
     participants
    1.09
     donors
    1.08
     believers
    1.08
    Act Density 0.213%

    No Known Activations