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

    Neuronpedia

    INDEX
    Explanations

    numbers or percentage values related to statistics or geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to the number 47

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Collider
    -0.73
    ¥ŀ
    -0.65
    urus
    -0.65
    unity
    -0.63
    agine
    -0.62
     actu
    -0.61
     coordin
    -0.61
    ovie
    -0.60
    uve
    -0.60
     fres
    -0.59
    POSITIVE LOGITS
    00
    0.98
    MJ
    0.90
    rpm
    0.86
     msec
    0.77
    328
    0.75
    inosaur
    0.75
    345
    0.73
    oslov
    0.73
    765
    0.73
    dfx
    0.73
    Act Density 0.033%

    No Known Activations