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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social issues and historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cu
    -0.15
    composite
    -0.15
     Noon
    -0.14
    _Renderer
    -0.14
     susp
    -0.14
     Harm
    -0.13
    Prepare
    -0.13
    bis
    -0.13
     salute
    -0.13
     insp
    -0.13
    POSITIVE LOGITS
     after
    0.30
    after
    0.25
     efter
    0.23
     поÑģле
    0.22
     dopo
    0.22
     après
    0.22
     AFTER
    0.21
    After
    0.21
    _after
    0.20
     aftermath
    0.20
    Act Density 0.674%

    No Known Activations