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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs related to actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .googleapis
    -0.16
    umeric
    -0.16
    ayers
    -0.16
    bread
    -0.16
    ÙĩÙħ
    -0.15
    dale
    -0.15
    asted
    -0.15
    iser
    -0.14
    ffect
    -0.14
    utm
    -0.14
    POSITIVE LOGITS
    ding
    0.33
    dings
    0.26
    ded
    0.25
    nesday
    0.24
    ders
    0.22
    dy
    0.22
    ddd
    0.20
    ges
    0.20
    DED
    0.20
    iot
    0.18
    Act Density 0.008%

    No Known Activations