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

    Neuronpedia

    INDEX
    Explanations

    expressions related to social impact and community assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikes
    -0.14
    sn
    -0.14
    aison
    -0.14
    æ¼Ķ
    -0.13
    ards
    -0.13
    sm
    -0.13
     uplifting
    -0.13
    520
    -0.13
     Surgical
    -0.13
     Credits
    -0.13
    POSITIVE LOGITS
    ensch
    0.15
    elps
    0.15
    errupt
    0.15
    pie
    0.15
    ilim
    0.15
    raphics
    0.15
    ó
    0.14
    storybook
    0.14
    vice
    0.14
    eras
    0.14
    Act Density 0.414%

    No Known Activations