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

    Neuronpedia

    INDEX
    Explanations

    terms related to profiles and principles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     habet
    -0.66
    tagext
    -0.64
     pleaſure
    -0.61
     ſont
    -0.60
    SqlCommand
    -0.60
     pneu
    -0.60
     pageNo
    -0.60
     setColor
    -0.59
     gameOver
    -0.59
    ſelves
    -0.59
    POSITIVE LOGITS
     Schmitz
    0.45
     PROFILE
    0.43
     Mitchell
    0.41
     Fitz
    0.40
    <i>
    0.40
     profile
    0.40
     Levy
    0.40
     Schmid
    0.39
    züge
    0.39
     Profile
    0.39
    Act Density 0.567%

    No Known Activations