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

    Neuronpedia

    INDEX
    Explanations

    quotes or statements made by people

    oai_token-act-pair · gpt-3.5-turbo

    the verb "said" and variations of it throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥİ
    -0.77
    ãĥ¼ãĥĨãĤ£
    -0.74
    TABLE
    -0.69
    atible
    -0.62
    ãĥĥãĥĪ
    -0.62
    à¦
    -0.61
    Appearances
    -0.61
    Charge
    -0.61
    estine
    -0.59
    Frameworks
    -0.58
    POSITIVE LOGITS
     sarcast
    0.87
     anecd
    0.83
     bluntly
    0.81
     rhet
    0.78
     diplom
    0.74
     emphatically
    0.70
    mson
    0.68
     adding
    0.67
     KR
    0.66
     afterward
    0.64
    Act Density 0.129%

    No Known Activations