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

    Neuronpedia

    INDEX
    Explanations

    terms and references related to software tools and applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angered
    -0.80
    amous
    -0.79
    )=
    -0.73
    ocaust
    -0.70
    said
    -0.69
    angering
    -0.69
    lesiastical
    -0.69
     slaughtered
    -0.68
    ultural
    -0.67
    #$#$
    -0.67
    POSITIVE LOGITS
    Plugin
    1.21
     plugin
    1.19
     Plugin
    1.18
    Tools
    1.13
    Tool
    1.11
     plugins
    1.07
     Tools
    1.04
     Tool
    1.02
    Widget
    0.99
     Extensions
    0.96
    Act Density 0.126%

    No Known Activations