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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating positions, roles, or achievements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñģок
    -0.15
    oso
    -0.15
    onto
    -0.14
    ÏĥÏħ
    -0.14
    ocene
    -0.14
     someone
    -0.14
    finalize
    -0.14
    onso
    -0.14
    leur
    -0.13
    aket
    -0.13
    POSITIVE LOGITS
     stint
    0.20
     series
    0.19
     brief
    0.16
     scholarship
    0.16
    ç³»åĪĹ
    0.16
     succession
    0.15
     suite
    0.15
     serie
    0.15
     obs
    0.15
    imson
    0.14
    Act Density 0.135%

    No Known Activations