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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "other" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ven
    -0.18
    ryn
    -0.17
    koli
    -0.16
    utan
    -0.16
    ycz
    -0.16
    fty
    -0.16
    ray
    -0.15
    ilar
    -0.15
    rong
    -0.15
    rames
    -0.14
    POSITIVE LOGITS
    world
    0.28
    ewise
    0.26
    wis
    0.23
    word
    0.23
     than
    0.23
    _than
    0.22
    ness
    0.21
    -than
    0.21
    -world
    0.20
    ullo
    0.20
    Act Density 0.080%

    No Known Activations