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

    Neuronpedia

    INDEX
    Explanations

    actions or decisions being taken

    oai_token-act-pair · gpt-3.5-turbo

    actions and decisions related to legal or official processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    comes
    -0.65
     itch
    -0.62
    ãĥĪ
    -0.61
    iciency
    -0.58
    ggles
    -0.58
    ãģĦ
    -0.58
    ãĥĻ
    -0.57
     Goo
    -0.56
    Pop
    -0.56
    ãĥ©ãĥ³
    -0.56
    POSITIVE LOGITS
     whereby
    0.92
     regarding
    0.85
     by
    0.79
    oux
    0.72
     against
    0.68
     concerning
    0.67
     Albion
    0.66
     towards
    0.65
    acial
    0.64
    encing
    0.64
    Act Density 0.215%

    No Known Activations