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

    Neuronpedia

    INDEX
    Explanations

    the verb "seeing" followed by a variety of objects or actions, possibly related to observation or perception

    oai_token-act-pair · gpt-3.5-turbo

    expressions and phrases related to observation or witnessing events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     preventive
    -0.60
     maintains
    -0.59
     ensures
    -0.59
     antid
    -0.58
     ascert
    -0.57
     ensured
    -0.57
    ufact
    -0.57
     paternal
    -0.57
     fundament
    -0.56
    angan
    -0.56
    POSITIVE LOGITS
     unfold
    1.21
     firsthand
    0.92
     crumble
    0.90
     emerge
    0.80
     grow
    0.75
     evolve
    0.74
     afar
    0.74
     fade
    0.73
    amorph
    0.72
     slide
    0.71
    Act Density 0.670%

    No Known Activations