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

    Neuronpedia

    INDEX
    Explanations

    instances of things being sent somewhere

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "sent."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etus
    -0.80
    ãĤ¨
    -0.72
    lihood
    -0.66
    Spoiler
    -0.65
    urity
    -0.65
     Alban
    -0.63
    externalActionCode
    -0.63
    thur
    -0.61
    LOD
    -0.60
    cube
    -0.60
    POSITIVE LOGITS
    inel
    1.10
     sent
    1.01
    sent
    0.83
     send
    0.82
    entary
    0.81
    nesday
    0.80
     emailed
    0.78
    mail
    0.78
    entious
    0.78
    iments
    0.77
    Act Density 0.018%

    No Known Activations