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

    Neuronpedia

    INDEX
    Explanations

    organizations or groups

    oai_token-act-pair · gpt-3.5-turbo

    terms related to governmental and official entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roma
    -0.90
    onymous
    -0.82
    ggle
    -0.82
    bsite
    -0.77
    issan
    -0.75
    outine
    -0.70
    mson
    -0.69
    udeau
    -0.68
    efully
    -0.68
    ...]
    -0.68
    POSITIVE LOGITS
     members
    0.81
     regulars
    0.81
     staffers
    0.79
     officials
    0.74
     veterans
    0.74
     opponents
    0.73
     employees
    0.73
     exclus
    0.72
     projections
    0.72
     successors
    0.71
    Act Density 0.688%

    No Known Activations