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

    Neuronpedia

    INDEX
    Explanations

    politically-related words and terms in various languages

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to politics and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Events
    -0.80
     GOODMAN
    -0.75
    Beat
    -0.74
    Ó
    -0.73
    Story
    -0.73
    Topics
    -0.72
    Reloaded
    -0.71
    OSH
    -0.71
    ãĥķãĤ©
    -0.70
    ãĥ¼ãĥĨãĤ£
    -0.70
    POSITIVE LOGITS
     hr
    0.75
    oca
    0.73
     pu
    0.70
     li
    0.69
    opt
    0.68
    bis
    0.68
     nat
    0.68
     shaft
    0.66
     exting
    0.66
     tion
    0.66
    Act Density 0.208%

    No Known Activations