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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing extremity or intensity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the article "a" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iments
    -0.80
    angles
    -0.79
    arten
    -0.76
    etsk
    -0.75
    reports
    -0.75
     amounts
    -0.74
    ATURES
    -0.73
    Effects
    -0.72
    ources
    -0.70
     Examples
    -0.69
    POSITIVE LOGITS
     bunch
    0.93
     dozen
    0.90
     nutshell
    0.88
     single
    0.86
     century
    0.85
     multitude
    0.83
     few
    0.83
     couple
    0.82
     thousand
    0.82
     nonexistent
    0.82
    Act Density 0.209%

    No Known Activations