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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hearing, listening, or being aware of information or stories

    oai_token-act-pair · gpt-3.5-turbo

    expressions of human experiences and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hest
    -0.87
    afort
    -0.77
    inth
    -0.77
    ensis
    -0.76
    emption
    -0.75
    enthal
    -0.73
    rity
    -0.71
    externalActionCode
    -0.70
    ãĥ´ãĤ¡
    -0.70
    etz
    -0.69
    POSITIVE LOGITS
     commenters
    1.26
     pundits
    1.25
     anecdotes
    1.23
     commentators
    1.21
     people
    1.20
     stories
    1.17
     excuses
    1.17
     articles
    1.15
     bloggers
    1.13
     folks
    1.13
    Act Density 0.496%

    No Known Activations