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

    Neuronpedia

    INDEX
    Explanations

    references to accidents and safety hazards in public spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Facial
    -0.18
     Friedman
    -0.17
    çĵľ
    -0.16
     Fence
    -0.15
    OTO
    -0.15
    agra
    -0.15
    fad
    -0.15
     feder
    -0.15
     FedEx
    -0.15
    FIELD
    -0.15
    POSITIVE LOGITS
     floor
    0.59
     floors
    0.48
    floor
    0.48
    -floor
    0.44
    flo
    0.43
     Floor
    0.43
    loor
    0.42
    Floor
    0.42
    Flo
    0.42
     flooring
    0.41
    Act Density 0.077%

    No Known Activations