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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "content."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    keleton
    -0.16
    Intensity
    -0.15
    ULA
    -0.15
    atical
    -0.15
    head
    -0.15
    ekler
    -0.14
    olumn
    -0.14
    ods
    -0.14
    åįĵ
    -0.14
    ÑİÑģÑĮ
    -0.14
    POSITIVE LOGITS
    rovers
    0.23
    ubern
    0.20
    emporary
    0.20
     Kont
    0.20
    essa
    0.20
    igs
    0.19
    rolling
    0.18
     cont
    0.18
     Cont
    0.18
    inent
    0.17
    Act Density 0.016%

    No Known Activations