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

    Neuronpedia

    INDEX
    Explanations

    adjectives and verbs related to feeling satisfied or pleased

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "content" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rolet
    -0.76
    udeb
    -0.67
     Siem
    -0.65
     Dee
    -0.64
    bsite
    -0.62
     Hurricanes
    -0.61
     Phant
    -0.60
     damn
    -0.59
    ipers
    -0.58
    iami
    -0.58
    POSITIVE LOGITS
    edly
    1.44
    ioned
    0.98
    ment
    0.97
    ions
    0.93
    iar
    0.87
    ious
    0.85
     content
    0.83
    tons
    0.81
    ional
    0.79
    ed
    0.79
    Act Density 0.017%

    No Known Activations