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

    Neuronpedia

    INDEX
    Explanations

    short phrases related to technology or computer terms

    oai_token-act-pair · gpt-3.5-turbo

    the presence of a specific character or symbol that appears frequently in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mathemat
    -0.79
    ĵĺ
    -0.74
    odium
    -0.73
    ammy
    -0.73
     misunder
    -0.71
    inav
    -0.71
     lawy
    -0.69
     disadvant
    -0.69
     triv
    -0.67
     carbohyd
    -0.67
    POSITIVE LOGITS
    ï¸ı
    1.35
    ¯¯
    0.95
    ship
    0.95
    ï¸
    0.88
    ¯
    0.86
    ··
    0.86
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.78
    âģ
    0.78
    ¯¯¯¯
    0.78
    £
    0.76
    Act Density 0.301%

    No Known Activations