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

    Neuronpedia

    INDEX
    Explanations

    technical computer terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to celebrations and social events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tud
    -0.51
     marrow
    -0.49
    ".[
    -0.47
     aud
    -0.46
     Blair
    -0.46
     Anim
    -0.45
     semin
    -0.45
     Bol
    -0.43
     âĢİ
    -0.42
     sed
    -0.42
    POSITIVE LOGITS
    ãĥĺãĥ©
    0.63
    ©¶æ
    0.62
    etheless
    0.61
    è¦ļéĨĴ
    0.61
    ucer
    0.61
    ailability
    0.59
    ignty
    0.57
    ģ«
    0.57
     tradem
    0.57
    intendent
    0.57
    Act Density 2.914%

    No Known Activations