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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "right" in close proximity to prepositions or other contextual cues

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating physical presence or location in time and space

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iple
    -0.78
    vari
    -0.73
    orously
    -0.70
    iatric
    -0.70
    ply
    -0.70
    marine
    -0.68
    amar
    -0.68
    uscript
    -0.68
    imens
    -0.67
    ravel
    -0.67
    POSITIVE LOGITS
     doorstep
    0.67
     Shooter
    0.65
    enegger
    0.63
     Wrong
    0.63
    edge
    0.60
     Stockholm
    0.59
     Bolt
    0.59
     Guns
    0.58
     Hog
    0.58
     Centre
    0.58
    Act Density 0.077%

    No Known Activations