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

    Neuronpedia

    INDEX
    Explanations

    words related to society, community, and personal life

    oai_token-act-pair · gpt-3.5-turbo

    references to social issues and their impact on individuals' lives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urat
    -0.75
    POR
    -0.73
    escription
    -0.69
    Sov
    -0.65
    iago
    -0.62
     Sisters
    -0.61
    anche
    -0.61
     rib
    -0.60
    itars
    -0.58
    urances
    -0.57
    POSITIVE LOGITS
    advertising
    0.74
    manship
    0.73
    âĢķ
    0.72
     circles
    0.72
     Indies
    0.71
     hierarchy
    0.69
     attRot
    0.66
     contexts
    0.66
     exponentially
    0.65
     vicinity
    0.63
    Act Density 0.440%

    No Known Activations