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

    Neuronpedia

    INDEX
    Explanations

    occurrences of text formatting tokens and references to specific variables or elements in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assemblée
    -0.53
     refusal
    -0.48
    تقاوى
    -0.47
     pacing
    -0.45
     Edwards
    -0.45
     punishment
    -0.44
     fundamental
    -0.44
     Tracking
    -0.44
     }}</
    -0.43
     tracking
    -0.43
    POSITIVE LOGITS
    stylers
    0.47
    sup
    0.45
    \{\\
    0.44
     bershka
    0.43
     Efq
    0.43
    arote
    0.40
    Received
    0.39
    Runtime
    0.37
    astéroïdes
    0.36
    contentLoaded
    0.36
    Act Density 0.185%

    No Known Activations