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

    Neuronpedia

    INDEX
    Explanations

    terms related to the field of science

    oai_token-act-pair · gpt-3.5-turbo

    references to science and scientific topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raine
    -0.72
     STATES
    -0.68
     Kessler
    -0.66
     Hearts
    -0.65
    rez
    -0.64
    ership
    -0.60
    zik
    -0.60
    âĢ¢âĢ¢
    -0.60
    igans
    -0.60
     Seasons
    -0.60
    POSITIVE LOGITS
     fiction
    1.36
     Fiction
    1.22
    icist
    1.07
    fiction
    0.99
     literacy
    0.95
    craft
    0.84
     disciplines
    0.83
     labs
    0.83
     experiments
    0.81
     sciences
    0.79
    Act Density 0.049%

    No Known Activations