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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "much of" followed by a topic or concept

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a sense of quantity or frequency in relation to something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.73
     dstg
    -0.71
     confir
    -0.68
    EStream
    -0.68
     ambassadors
    -0.64
     stacks
    -0.62
     Proxy
    -0.59
     EDIT
    -0.58
     Soldiers
    -0.58
    bid
    -0.58
    POSITIVE LOGITS
    ãĤ¢ãĥ«
    0.76
    ãĥĬ
    0.71
    ãĥ³
    0.68
     Coverage
    0.66
    stay
    0.66
    ãĤ¹
    0.65
     Nort
    0.65
    ourn
    0.65
     course
    0.64
    ãĥ´ãĤ¡
    0.64
    Act Density 0.066%

    No Known Activations