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

    Neuronpedia

    INDEX
    Explanations

    references to plugins and their functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     acoged
    -0.48
     betweenstory
    -0.47
     nakalista
    -0.41
     acogedor
    -0.41
     Umum
    -0.41
     animación
    -0.40
     JUSTICE
    -0.38
    Décès
    -0.38
     ře
    -0.37
     envejec
    -0.36
    POSITIVE LOGITS
     plugin
    1.19
     Plugin
    1.16
     plugins
    1.12
    Plugin
    1.09
    plugin
    1.08
     Plugins
    1.07
    Plugins
    0.97
    plugins
    0.94
    lugin
    0.94
    插件
    0.89
    Act Density 0.548%

    No Known Activations