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

    Neuronpedia

    INDEX
    Explanations

    important concepts or terms related to crucial components and aspects within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apses
    -0.87
    events
    -0.85
    ancies
    -0.84
    oops
    -0.83
    bows
    -0.81
    lees
    -0.76
    brids
    -0.76
    aucuses
    -0.76
    abilities
    -0.75
    iencies
    -0.75
    POSITIVE LOGITS
     contributor
    1.20
     indicator
    1.20
    stay
    1.14
     reminder
    1.14
     fixture
    1.14
     contender
    1.13
     staple
    1.13
     source
    1.10
     deterrent
    1.08
     example
    1.07
    Act Density 0.087%

    No Known Activations