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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific people or organizations in a context related to news or politics

    oai_token-act-pair · gpt-3.5-turbo

    references to political actions and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rian
    -0.45
    rylic
    -0.44
     Frag
    -0.44
    gravity
    -0.43
    avez
    -0.42
    lag
    -0.41
    ividual
    -0.40
    itamin
    -0.39
    ursed
    -0.39
    riel
    -0.38
    POSITIVE LOGITS
     corrid
    0.50
    entimes
    0.49
    ĵĺ
    0.49
    wcs
    0.48
     thous
    0.47
    terness
    0.45
     Gutierrez
    0.45
     newcom
    0.44
    ©¶æ¥µ
    0.43
     suspic
    0.43
    Act Density 9.358%

    No Known Activations