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

    Neuronpedia

    INDEX
    Explanations

    phrases related to going out and social activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plex
    -0.17
    chr
    -0.17
    498
    -0.15
    osc
    -0.15
    ult
    -0.15
    ove
    -0.14
     going
    -0.14
    ноз
    -0.14
    ato
    -0.14
     premium
    -0.13
    POSITIVE LOGITS
    doors
    0.21
    wards
    0.19
    кÑĢаÑĹ
    0.16
     cá»Ļng
    0.16
     onto
    0.16
    SIDE
    0.16
     doors
    0.15
    placement
    0.15
    Into
    0.15
    skirts
    0.15
    Act Density 0.045%

    No Known Activations