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

    Neuronpedia

    INDEX
    Explanations

    proper names or acronyms related to groups or organizations

    oai_token-act-pair · gpt-3.5-turbo

    financial and organizational terminology related to groups and positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¶
    -0.91
    xes
    -0.89
    esa
    -0.87
    ibur
    -0.86
    EO
    -0.82
    ãĤ·ãĥ£
    -0.80
    OX
    -0.79
    eways
    -0.79
    ãĤª
    -0.78
    hyde
    -0.76
    POSITIVE LOGITS
     Group
    1.09
    group
    1.01
     group
    0.98
     grouping
    0.97
    Group
    0.96
    roups
    0.95
     GROUP
    0.91
     Groups
    0.90
    roup
    0.88
    List
    0.84
    Act Density 0.294%

    No Known Activations