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

    Neuronpedia

    INDEX
    Explanations

    quotes by individuals addressed to reporters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "reporters."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inho
    -0.76
    tein
    -0.71
    vasive
    -0.67
    reme
    -0.67
    ez
    -0.67
    pha
    -0.65
    ham
    -0.65
    ston
    -0.65
    uras
    -0.64
    uay
    -0.62
    POSITIVE LOGITS
    perty
    0.82
     onstage
    0.71
    hip
    0.71
    orage
    0.71
    iets
    0.70
     gathered
    0.70
     assembled
    0.70
     reporters
    0.69
    hips
    0.68
     backstage
    0.67
    Act Density 0.027%

    No Known Activations