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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote a formal or structured approach to topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aille
    -0.14
    RATION
    -0.14
     inherited
    -0.14
    quette
    -0.14
    :!
    -0.14
     بس
    -0.14
    tracted
    -0.14
    442
    -0.14
    Fallback
    -0.14
    phere
    -0.14
    POSITIVE LOGITS
     tale
    0.28
     look
    0.25
     Tale
    0.24
     guide
    0.24
     primer
    0.23
     Look
    0.23
     Guide
    0.22
     Case
    0.21
     Clo
    0.21
     Primer
    0.20
    Act Density 0.090%

    No Known Activations