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

    Neuronpedia

    INDEX
    Explanations

    words related to news articles and online content

    oai_token-act-pair · gpt-3.5-turbo

    the letter "S" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     techno
    -0.69
     bottleneck
    -0.68
    EStream
    -0.67
     unrestricted
    -0.67
     CPR
    -0.67
     laureate
    -0.66
    catentry
    -0.65
    puter
    -0.65
     crib
    -0.65
     downed
    -0.64
    POSITIVE LOGITS
    AND
    1.18
    OUND
    1.18
    ESSION
    1.16
    UD
    1.12
    ustain
    1.12
    UM
    1.12
    RS
    1.10
    WE
    1.10
    ELF
    1.08
    UR
    1.06
    Act Density 0.045%

    No Known Activations