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

    Neuronpedia

    INDEX
    Explanations

    terms related to anticipation and hints regarding upcoming content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .backup
    -0.14
    465
    -0.13
    alez
    -0.13
    ilda
    -0.13
     testimon
    -0.13
    UniqueId
    -0.13
    ãĥ³ãĥĩãĤ£
    -0.13
    ponge
    -0.13
    dik
    -0.13
    iyah
    -0.13
    POSITIVE LOGITS
     teas
    0.40
     tease
    0.38
     teased
    0.36
     teasing
    0.34
     teaser
    0.33
     crypt
    0.33
     hint
    0.32
     preview
    0.30
     hints
    0.29
     Hint
    0.29
    Act Density 0.213%

    No Known Activations