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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases indicating potential outcomes or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĪи
    -0.15
    atron
    -0.15
    odem
    -0.15
    رÛĮز
    -0.15
    isoner
    -0.14
    Äįer
    -0.14
    ãĥ³ãĥ
    -0.14
    /GPL
    -0.14
    ÑģÑĤв
    -0.14
    icont
    -0.13
    POSITIVE LOGITS
     soon
    0.32
     Soon
    0.26
    soon
    0.25
    Soon
    0.22
     sỼm
    0.18
     possibly
    0.17
     headed
    0.17
     upcoming
    0.17
     potentially
    0.17
     be
    0.16
    Act Density 0.095%

    No Known Activations