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

    Neuronpedia

    INDEX
    Explanations

    negations or words indicating the absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zeug
    -0.16
    ruc
    -0.15
    ει
    -0.15
    ãģĦãĤĦ
    -0.14
    Ñĥки
    -0.14
    sometimes
    -0.14
    aler
    -0.14
    undan
    -0.14
    384
    -0.13
    USH
    -0.13
    POSITIVE LOGITS
     surprising
    0.28
     unique
    0.25
     altogether
    0.24
    unique
    0.24
     surpr
    0.23
     unexpected
    0.22
     unprecedented
    0.22
     unusual
    0.20
     news
    0.20
     surprise
    0.20
    Act Density 0.099%

    No Known Activations