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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or specific names

    oai_token-act-pair · gpt-3.5-turbo

    sentences beginning with "It" that describe various subjects or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĺħ
    -0.69
     Reading
    -0.64
     Destiny
    -0.62
    GROUND
    -0.61
     bothering
    -0.60
     Done
    -0.59
     Saying
    -0.59
     Lyme
    -0.58
     Kris
    -0.58
     distraction
    -0.58
    POSITIVE LOGITS
     consists
    1.25
     comprises
    1.22
     differs
    1.17
     possesses
    1.05
    self
    1.05
     weighs
    1.04
     occupies
    1.02
     lacks
    1.02
     contains
    1.01
     resembles
    1.01
    Act Density 0.150%

    No Known Activations