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

    Neuronpedia

    INDEX
    Explanations

    phrases related to constraints or restrictions

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to constraints and limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.85
    ombies
    -0.80
    mberg
    -0.79
    Downloadha
    -0.76
    ï¸
    -0.75
    ppo
    -0.75
    phe
    -0.74
    =-=-
    -0.72
    grab
    -0.72
    ocene
    -0.69
    POSITIVE LOGITS
    abulary
    1.07
    ipation
    1.01
    ellation
    1.00
    expr
    0.96
     pige
    0.96
     const
    0.90
    ricting
    0.83
    rued
    0.81
    rast
    0.81
     pigeon
    0.80
    Act Density 0.005%

    No Known Activations