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

    Neuronpedia

    INDEX
    Explanations

    phrases related to involvement in activities or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate participation or involvement in activities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.71
    yond
    -0.66
    aghan
    -0.63
     traveled
    -0.60
    izes
    -0.60
    ield
    -0.59
    quartered
    -0.58
    byss
    -0.58
    eger
    -0.58
    illac
    -0.58
    POSITIVE LOGITS
    OTA
    0.77
    cre
    0.70
    ricular
    0.63
    days
    0.62
     discussions
    0.60
    oco
    0.59
    Ear
    0.58
    Secure
    0.57
    7601
    0.57
     WW
    0.56
    Act Density 0.175%

    No Known Activations