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

    Neuronpedia

    INDEX
    Explanations

    adjectives or phrases related to strength, sharpness, and importance

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to soundness, strength, and security in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pwr
    -0.71
     âĨij
    -0.68
     Freeze
    -0.64
    trak
    -0.64
     Originally
    -0.63
    ilogy
    -0.62
    ridor
    -0.62
     Curse
    -0.61
     Puzzle
    -0.61
     Loren
    -0.61
    POSITIVE LOGITS
     truths
    1.19
     minds
    1.09
    ness
    1.08
    minded
    1.07
     ideas
    1.02
     thinkers
    1.01
     ideals
    1.00
     outcomes
    1.00
     solutions
    0.98
     ideologies
    0.98
    Act Density 0.352%

    No Known Activations