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

    Neuronpedia

    INDEX
    Explanations

    expressions of excitement and anticipation related to announcements or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     arguments
    -0.54
    DockStyle
    -0.51
    IGraphics
    -0.49
     оригіналу
    -0.48
    allenge
    -0.48
    GIVEREF
    -0.48
     criticisms
    -0.47
     Suggestions
    -0.47
     critics
    -0.47
     criticism
    -0.47
    POSITIVE LOGITS
     inform
    1.64
     informing
    1.58
     informs
    1.57
     informed
    1.55
     announce
    1.46
     announced
    1.44
    inform
    1.30
     announces
    1.29
     Inform
    1.29
     announcing
    1.28
    Act Density 0.479%

    No Known Activations