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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate actions or obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pong
    -0.16
    tridge
    -0.15
    peare
    -0.15
    PF
    -0.14
    osome
    -0.14
     Jennings
    -0.13
    ove
    -0.13
     regards
    -0.13
    äre
    -0.13
    ore
    -0.13
    POSITIVE LOGITS
    пÑĢимеÑĢ
    0.16
    ALSE
    0.15
    awks
    0.15
    cher
    0.14
    elper
    0.14
     blues
    0.14
    -know
    0.14
    اث
    0.14
    rious
    0.13
    821
    0.13
    Act Density 0.062%

    No Known Activations