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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "that"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĤãĤĬ
    -0.20
    ãģĤãĤĭ
    -0.20
    idon
    -0.17
    idan
    -0.16
     there
    -0.15
    iya
    -0.15
    iy
    -0.14
    ursors
    -0.14
    iangle
    -0.14
    (
    -0.13
    POSITIVE LOGITS
    ched
    0.21
    ching
    0.21
    ch
    0.19
    ches
    0.17
    oping
    0.17
     has
    0.16
    chy
    0.16
    /on
    0.15
    Ú©Ø´
    0.14
    alin
    0.14
    Act Density 0.247%

    No Known Activations