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

    Neuronpedia

    INDEX
    Explanations

    phrases related to abilities and potential capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mention
    -0.16
    _mentions
    -0.15
    vise
    -0.15
     Mention
    -0.15
    otime
    -0.14
    ableObject
    -0.14
    abus
    -0.14
    ulings
    -0.14
    anooga
    -0.14
     ($.
    -0.14
    POSITIVE LOGITS
     describe
    0.35
     describing
    0.33
     describes
    0.33
     description
    0.32
     descri
    0.31
     descriptions
    0.30
    æııè¿°
    0.29
     Describe
    0.28
    description
    0.28
     described
    0.27
    Act Density 0.018%

    No Known Activations