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

    Neuronpedia

    INDEX
    Explanations

    locations or venues related to events or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to venues or places with "hall" in their names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orses
    -0.70
     Native
    -0.64
     Flip
    -0.63
     Planned
    -0.60
     position
    -0.59
     newborn
    -0.58
    ��
    -0.57
     rubber
    -0.57
     error
    -0.57
     tires
    -0.57
    POSITIVE LOGITS
    hall
    4.79
    Hall
    1.96
     hall
    1.62
     Hall
    1.44
     halls
    1.42
    halla
    1.36
    hill
    1.35
    hower
    1.21
     Halls
    1.18
    haw
    1.05
    Act Density 0.010%

    No Known Activations