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

    Neuronpedia

    INDEX
    Explanations

    phrases related to academic disciplines and departments

    oai_token-act-pair · gpt-3.5-turbo

    references to academic faculties or fields of study

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     blister
    -0.90
     resent
    -0.87
     tremend
    -0.86
     flaw
    -0.85
     regress
    -0.84
     clen
    -0.82
     slump
    -0.82
     egreg
    -0.82
     stagger
    -0.81
     aven
    -0.80
    POSITIVE LOGITS
     Clothing
    1.65
     Educational
    1.59
     Miscellaneous
    1.56
     Recreation
    1.53
     Sports
    1.51
     Programming
    1.50
     Electronics
    1.50
     Healthcare
    1.49
     Fitness
    1.48
     Engineering
    1.46
    Act Density 0.332%

    No Known Activations