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

    Neuronpedia

    INDEX
    Explanations

    terms related to measurements, efficiency, constraints, merits, wisdom, love, belief, role, integrity, resistance, probability, expectations, emotion, chaos, predictability, and security

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to efficiency, metrics, and the assessment of value or standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sic
    -0.73
    gow
    -0.70
    arnaev
    -0.68
    cas
    -0.68
    AMA
    -0.67
    jay
    -0.66
     Tanz
    -0.65
    ahon
    -0.64
    kus
    -0.64
    thumbnails
    -0.64
    POSITIVE LOGITS
     binds
    0.85
     arises
    0.84
     affecting
    0.83
     affects
    0.78
     consists
    0.78
     lasts
    0.75
    uous
    0.74
    olver
    0.73
     satisfies
    0.73
     arising
    0.73
    Act Density 0.477%

    No Known Activations