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

    Neuronpedia

    INDEX
    Explanations

    elements related to mystery, puzzles, and detective work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.80
     forState
    -0.79
    avyzd
    -0.75
    DebuggerNonUser
    -0.74
    IntoConstraints
    -0.70
    HtmlAttribute
    -0.67
     bershka
    -0.67
     purpoſe
    -0.67
    ftagPool
    -0.67
    createObject
    -0.67
    POSITIVE LOGITS
     puzzle
    1.57
     mystery
    1.57
     puzzles
    1.48
     riddle
    1.46
    mystery
    1.35
     mysteries
    1.30
     Puzzle
    1.29
     Mystery
    1.27
    Mystery
    1.25
     riddles
    1.25
    Act Density 0.648%

    No Known Activations