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

    Neuronpedia

    INDEX
    Explanations

    phrases where an opinion or input is provided

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "weigh in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CLASSIFIED
    -0.74
    CVE
    -0.70
    =]
    -0.68
    STER
    -0.66
    soever
    -0.65
    lvl
    -0.62
    dar
    -0.58
    killed
    -0.58
    ":"/
    -0.58
    ŀ
    -0.57
    POSITIVE LOGITS
    ordinate
    1.02
    clusions
    1.01
     unison
    0.99
     accordance
    0.95
     favor
    0.91
     lieu
    0.91
     conjunction
    0.90
     vitro
    0.89
     favour
    0.88
    between
    0.88
    Act Density 0.165%

    No Known Activations