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

    Neuronpedia

    INDEX
    Explanations

    words related to confirmation or verification

    oai_token-act-pair · gpt-3.5-turbo

    the word "indeed" and its frequency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    center
    -0.66
    isson
    -0.60
     Lessons
    -0.59
    Ĺ
    -0.58
    Cooldown
    -0.58
    Mesh
    -0.58
     Units
    -0.57
     Picks
    -0.57
    Central
    -0.57
     Soldiers
    -0.57
    POSITIVE LOGITS
    ional
    0.95
    NESS
    0.79
    uala
    0.77
    EngineDebug
    0.77
     qualifies
    0.74
    actory
    0.74
    eem
    0.73
     indeed
    0.72
     exist
    0.67
     hers
    0.67
    Act Density 0.015%

    No Known Activations