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

    Neuronpedia

    INDEX
    Explanations

    phrases related to online platforms or communities

    oai_token-act-pair · gpt-3.5-turbo

    references to social media platforms and specific groups or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibi
    -0.76
    owicz
    -0.73
    renheit
    -0.72
     Dickens
    -0.71
     Ellis
    -0.70
    ©¶æ¥µ
    -0.68
    olphin
    -0.68
    Tap
    -0.68
    clair
    -0.67
    Jer
    -0.66
    POSITIVE LOGITS
     group
    2.28
    group
    2.11
     groups
    2.06
    Group
    2.06
     Groups
    2.06
    groups
    2.06
     Group
    1.99
     grouping
    1.93
    roups
    1.91
     GROUP
    1.89
    Act Density 0.494%

    No Known Activations