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

    Neuronpedia

    INDEX
    Explanations

    terms related to organizations or groups

    oai_token-act-pair · gpt-3.5-turbo

    terms related to groups and organizations, particularly in sports or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¢ãĥ«
    -0.72
     Vill
    -0.68
    zbek
    -0.64
    ãĥĥãĥĪ
    -0.64
     Lanka
    -0.63
    ãĥķãĤ©
    -0.62
     crude
    -0.61
    cott
    -0.60
    imon
    -0.60
    ãĥŃ
    -0.57
    POSITIVE LOGITS
    osphere
    1.02
     hierarchy
    0.88
     itself
    0.85
    geist
    0.83
    elight
    0.76
     quo
    0.75
    iest
    0.75
    's
    0.70
     faithful
    0.68
    ultimate
    0.68
    Act Density 0.349%

    No Known Activations