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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific objects or concepts, like "language," "phone," "tower design," "fighter," and "medical device."

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to various subjects of importance or concern, particularly in relation to societal issues and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »Ĵ
    -0.88
    ģĸ
    -0.76
     Marketable
    -0.74
    outube
    -0.72
    ¶ħ
    -0.71
    ĪĴ
    -0.71
    Ô
    -0.70
    ĸļ
    -0.69
    VIDIA
    -0.68
    Ļ½
    -0.66
    POSITIVE LOGITS
     itself
    0.96
    osphere
    0.90
    liest
    0.81
     microbiome
    0.79
    iest
    0.78
     nucleus
    0.76
     portion
    0.73
     industry
    0.72
     genre
    0.71
    problem
    0.70
    Act Density 0.470%

    No Known Activations