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

    Neuronpedia

    INDEX
    Explanations

    quantitative terms related to measurement and comparison

    oai_token-act-pair · gpt-3.5-turbo

    terms related to quantifiable entities and structures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Õ
    -0.80
    âĸ¬
    -0.78
    Ô
    -0.76
    ãĤ¨ãĥ«
    -0.73
    ãĥį
    -0.72
    Benz
    -0.71
    CHAR
    -0.70
    çĶ°
    -0.69
    ãĤ¿
    -0.69
    Tur
    -0.69
    POSITIVE LOGITS
    hips
    1.34
    poons
    1.20
    etting
    1.13
    ynthesis
    1.12
    hip
    1.10
    uggest
    1.10
    avers
    1.06
    heet
    1.05
    ourcing
    1.02
    ettings
    1.01
    Act Density 0.415%

    No Known Activations