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

    Neuronpedia

    INDEX
    Explanations

    references to associated press reporting or news content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -scalable
    -0.15
    432
    -0.15
    sth
    -0.15
    436
    -0.15
    çŃĨ
    -0.15
    ãĥĨãĥ«
    -0.14
    stoff
    -0.14
    utton
    -0.14
    tas
    -0.14
    354
    -0.14
    POSITIVE LOGITS
    plitude
    0.14
    Dialogue
    0.14
    letic
    0.14
    morgan
    0.14
    tvrt
    0.13
    oom
    0.13
     Dialogue
    0.13
     Snow
    0.13
    umi
    0.13
    usty
    0.13
    Act Density 0.005%

    No Known Activations