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

    Neuronpedia

    INDEX
    Explanations

    elements related to architectural details and structural features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chet
    -0.18
    hort
    -0.15
     cushions
    -0.15
     Cush
    -0.14
     Pins
    -0.14
    縮
    -0.13
     invit
    -0.13
    sher
    -0.13
     Dover
    -0.13
    amma
    -0.13
    POSITIVE LOGITS
     ceiling
    0.40
     ceilings
    0.39
     Ceiling
    0.33
     raft
    0.32
    -ce
    0.31
     поÑĤол
    0.29
     ceil
    0.29
     suspended
    0.28
     vault
    0.28
    ceil
    0.28
    Act Density 0.077%

    No Known Activations