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

    Neuronpedia

    INDEX
    Explanations

    words related to physical locations or landmarks

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns related to locations, events, and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    guyen
    -0.74
     TRUMP
    -0.61
    ccording
    -0.61
     Cosponsors
    -0.58
    TRUMP
    -0.56
    ACP
    -0.56
     Ellison
    -0.56
    =/
    -0.55
    akeru
    -0.53
    ĪĴ
    -0.52
    POSITIVE LOGITS
     ().
    0.62
     era
    0.62
     catalogue
    0.61
    $.
    0.55
    ]).
    0.54
     haha
    0.53
     forum
    0.53
    ultimate
    0.52
     arsenal
    0.52
    '.
    0.52
    Act Density 0.976%

    No Known Activations