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

    Neuronpedia

    INDEX
    Explanations

    text segments related to providing information or instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating action or instructions related to implementation and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iatus
    -0.81
    uan
    -0.71
     Leilan
    -0.69
    osaurus
    -0.69
    ulus
    -0.67
    ername
    -0.67
    abouts
    -0.67
    xual
    -0.66
    itage
    -0.65
    abama
    -0.64
    POSITIVE LOGITS
    âĵĺ
    0.94
    SOURCE
    0.85
    âĢł
    0.73
    ONEY
    0.72
    âĹ¼
    0.72
    gencies
    0.72
    FIG
    0.70
    database
    0.70
    Availability
    0.70
    Requires
    0.69
    Act Density 0.205%

    No Known Activations