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

    Neuronpedia

    INDEX
    Explanations

    key concepts and terms related to product and user experience improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DebuggerNonUser
    -0.72
    ########.
    -0.54
     doInBackground
    -0.53
    TintMode
    -0.53
     autorytatywna
    -0.52
     piante
    -0.46
    Controllo
    -0.46
     esternos
    -0.46
     innamor
    -0.46
    Most
    -0.46
    POSITIVE LOGITS
    spesies
    0.75
     unknownFields
    0.72
     BorderRadius
    0.71
     good
    0.70
    ^(@)
    0.67
     zło
    0.65
    Хорошо
    0.65
     better
    0.65
     Хорошо
    0.65
    NESDAY
    0.64
    Act Density 0.286%

    No Known Activations