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

    Neuronpedia

    INDEX
    Explanations

    phrases related to resolutions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    actions and emotional responses within interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    busters
    -0.88
    osate
    -0.86
    Critics
    -0.84
    ornia
    -0.80
     Critics
    -0.77
     Berman
    -0.75
    !'"
    -0.74
    SPONSORED
    -0.73
    govtrack
    -0.72
    cki
    -0.72
    POSITIVE LOGITS
     Jaune
    1.08
     Pyrrha
    1.02
     crimson
    0.88
     Weasley
    0.86
     grin
    0.86
     faint
    0.85
    blance
    0.83
     Naruto
    0.83
     potions
    0.83
     mage
    0.83
    Act Density 0.623%

    No Known Activations