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

    Neuronpedia

    INDEX
    Explanations

    phrases where someone is expressing their opinion emphatically

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "say" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =~=~
    -0.73
     fingerprints
    -0.67
     imprint
    -0.65
     chance
    -0.64
     Lauder
    -0.64
    ernandez
    -0.63
    outube
    -0.62
    ÅĤ
    -0.59
     âľĶ
    -0.59
    aird
    -0.58
    POSITIVE LOGITS
     goodbye
    0.74
     myself
    0.69
    eport
    0.67
     aloud
    0.66
     Izan
    0.64
    isson
    0.62
     Neph
    0.60
    gha
    0.60
    ql
    0.59
    nostic
    0.58
    Act Density 0.097%

    No Known Activations