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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "other."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bable
    -0.18
    ायन
    -0.16
    ible
    -0.15
    nable
    -0.14
    allenge
    -0.14
    ned
    -0.14
    aura
    -0.14
    fort
    -0.14
    ova
    -0.14
    illy
    -0.14
    POSITIVE LOGITS
    -than
    0.23
     than
    0.21
     niż
    0.20
    than
    0.20
    world
    0.20
    wis
    0.19
    /new
    0.19
    ëĿ¼ëıĦ
    0.18
    wh
    0.18
    ials
    0.18
    Act Density 0.104%

    No Known Activations