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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Text" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    letter
    -0.15
    931
    -0.15
     éģ
    -0.14
    ispecies
    -0.14
    taire
    -0.14
    먹
    -0.14
    Letter
    -0.14
    View
    -0.13
    rats
    -0.13
    flip
    -0.13
    POSITIVE LOGITS
    ured
    0.28
    ual
    0.28
    ural
    0.23
    URED
    0.23
    UAL
    0.22
    uring
    0.21
    ually
    0.21
    ura
    0.20
    ures
    0.20
    uality
    0.19
    Act Density 0.026%

    No Known Activations