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

    Neuronpedia

    INDEX
    Explanations

    numerical values in specific ranges

    oai_token-act-pair · gpt-3.5-turbo

    references to the number thirty in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lar
    -0.85
    omial
    -0.79
    ĸļ
    -0.78
    algia
    -0.76
    hers
    -0.75
    ality
    -0.74
    ates
    -0.73
    ation
    -0.72
    yrinth
    -0.72
    atorial
    -0.71
    POSITIVE LOGITS
    fps
    0.85
    nm
    0.83
    mph
    0.77
    utical
    0.75
    ¯¯
    0.74
    etheus
    0.72
     minutes
    0.70
    ×ķ
    0.69
     seconds
    0.68
     Seconds
    0.68
    Act Density 0.057%

    No Known Activations