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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant moments or turning points in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to significant moments or events in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    killed
    -0.69
    ŀ
    -0.64
    ubs
    -0.63
     exceptions
    -0.63
    leans
    -0.62
     inconsist
    -0.60
    LOG
    -0.60
     exception
    -0.60
    ratch
    -0.59
     waived
    -0.58
    POSITIVE LOGITS
     terms
    1.09
    efficiency
    1.06
     relation
    1.02
     regards
    1.01
    effic
    0.99
     favor
    0.94
     favour
    0.90
    escap
    0.90
     history
    0.89
    ordinate
    0.87
    Act Density 0.186%

    No Known Activations