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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical skills or job responsibilities

    oai_token-act-pair · gpt-3.5-turbo

    instances of slashes or divisions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carlton
    -0.75
     Grimes
    -0.71
     Giov
    -0.71
     irresist
    -0.70
     Syl
    -0.70
     Leilan
    -0.67
     Pigs
    -0.65
     creep
    -0.65
     Angelo
    -0.64
     accus
    -0.64
    POSITIVE LOGITS
    etc
    1.45
    whatever
    1.24
    Flickr
    1.04
    oct
    0.99
    workshop
    0.99
    pmwiki
    0.97
    coll
    0.97
    UV
    0.95
    CN
    0.94
    pol
    0.93
    Act Density 0.066%

    No Known Activations