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

    Neuronpedia

    INDEX
    Explanations

    terms related to academic journals and publications

    oai_token-act-pair · gpt-3.5-turbo

    references to academic journals and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ceilings
    -0.87
     likeness
    -0.84
     herds
    -0.76
     rooft
    -0.74
    endi
    -0.73
     oranges
    -0.72
     checkpoints
    -0.72
     mustache
    -0.71
     turrets
    -0.70
    ickr
    -0.70
    POSITIVE LOGITS
     Applied
    1.11
     Experimental
    1.09
     Psychology
    0.99
     Contemporary
    0.98
     Clinical
    0.96
     Molecular
    0.95
     Compar
    0.95
     Research
    0.94
     Mathemat
    0.94
     Economics
    0.93
    Act Density 0.042%

    No Known Activations