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

    Neuronpedia

    INDEX
    Explanations

    locations and settings mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    locations and settings described in detail

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERO
    -0.70
    emort
    -0.60
    henko
    -0.60
    orians
    -0.57
    onom
    -0.57
    encer
    -0.56
    rists
    -0.53
    alam
    -0.53
     evolves
    -0.53
     foresee
    -0.53
    POSITIVE LOGITS
     outskirts
    0.75
     southwest
    0.72
     downtown
    0.71
     nearby
    0.70
     southwestern
    0.69
     makeshift
    0.69
     plaza
    0.68
     adjoining
    0.68
     flats
    0.68
     village
    0.67
    Act Density 0.914%

    No Known Activations