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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases that express dependencies or variations based on different factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lette
    -0.18
    asaki
    -0.17
    iversite
    -0.16
    adel
    -0.15
    sko
    -0.15
    atak
    -0.15
     piger
    -0.14
    atism
    -0.14
    IMER
    -0.14
    schemas
    -0.14
    POSITIVE LOGITS
    <|begin_of_text|>
    0.18
    endent
    0.17
     upon
    0.16
    enti
    0.15
    kip
    0.15
    CES
    0.15
    elman
    0.14
    aul
    0.14
     sweetness
    0.14
     depending
    0.14
    Act Density 0.033%

    No Known Activations