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

    Neuronpedia

    INDEX
    Explanations

    terms related to making or completing something smoothly or cleanly

    oai_token-act-pair · gpt-3.5-turbo

    words associated with texture and quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DEV
    -0.68
    âĢ¢âĢ¢
    -0.68
     Canary
    -0.62
    STAR
    -0.62
     denomin
    -0.61
     Bots
    -0.61
     incumbent
    -0.61
     idol
    -0.59
    ŃĶ
    -0.59
     Practices
    -0.58
    POSITIVE LOGITS
    hed
    2.47
    hing
    2.45
    hes
    2.25
    hers
    2.02
    hest
    1.94
    htaking
    1.91
    her
    1.79
    he
    1.77
    hen
    1.76
    hens
    1.74
    Act Density 0.154%

    No Known Activations