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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating the beginning of actions or changes in state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    starting to [verb]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plegable
    -0.34
     endast
    -0.33
     reposo
    -0.32
     plazos
    -0.31
     value
    -0.31
    رائه
    -0.30
     graduación
    -0.30
     universel
    -0.30
     krep
    -0.30
     lâmpada
    -0.29
    POSITIVE LOGITS
     للاسماء
    0.88
    Tikang
    0.86
    weile
    0.82
     Starts
    0.74
     Beginnings
    0.67
    tvguidetime
    0.67
    ChildScrollView
    0.66
    Started
    0.65
     Started
    0.65
     مشين
    0.65
    Act Density 0.008%

    No Known Activations