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

    Neuronpedia

    INDEX
    Explanations

    references to personal development and support in achieving goals

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

    Tokens preceding infinitives or gerunds

    np_acts-logits-general · gemini-2.0-flash

    to improve or succeed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.97
    AndEndTag
    -0.77
    RegressionTest
    -0.77
    AddHtmlAttribute
    -0.74
     ModelExpression
    -0.72
     فريبيس
    -0.71
    StoryboardSegue
    -0.70
    enderror
    -0.68
    CompleteListener
    -0.68
    SBATCH
    -0.67
    POSITIVE LOGITS
     maximize
    0.73
     succeed
    0.73
     boost
    0.72
     increase
    0.71
     Increase
    0.70
    Increase
    0.70
     maximise
    0.69
     successfully
    0.67
     master
    0.67
    successfully
    0.66
    Act Density 0.173%

    No Known Activations