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

    Neuronpedia

    INDEX
    Explanations

    terms related to academic fields or research disciplines

    oai_token-act-pair · gpt-3.5-turbo

    references to academic programs or fields of study

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     speedy
    -0.69
     relent
    -0.67
     uncond
    -0.67
     respawn
    -0.66
     dirt
    -0.65
     blaze
    -0.64
    empt
    -0.64
     predictable
    -0.63
     custom
    -0.62
     set
    -0.62
    POSITIVE LOGITS
     Studies
    3.62
    Studies
    2.59
     studies
    2.20
     Study
    1.95
    Study
    1.67
    Research
    1.54
     Research
    1.47
     Researchers
    1.46
     Scholars
    1.32
    study
    1.32
    Act Density 0.018%

    No Known Activations