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

    Neuronpedia

    INDEX
    Explanations

    language that suggests emotional or nostalgic evocation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atur
    -0.17
    ycop
    -0.15
    rement
    -0.15
    leich
    -0.15
     DCHECK
    -0.15
    ebo
    -0.14
    rets
    -0.14
    iker
    -0.14
    raf
    -0.14
    Refreshing
    -0.14
    POSITIVE LOGITS
    297
    0.16
    nard
    0.15
     dom
    0.15
    ostel
    0.14
     ìĶ
    0.14
     cat
    0.14
    747
    0.14
     Repo
    0.14
     Emerson
    0.13
     güç
    0.13
    Act Density 0.019%

    No Known Activations