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

    Neuronpedia

    INDEX
    Explanations

    IP addresses or technical terms with the 'x' prefix

    oai_token-act-pair · gpt-3.5-turbo

    references to software versions and technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pru
    -0.79
     TODAY
    -0.61
     anonymity
    -0.60
    getic
    -0.60
    assetsadobe
    -0.60
     starters
    -0.59
     Sut
    -0.59
     compe
    -0.58
     stool
    -0.58
    DERR
    -0.58
    POSITIVE LOGITS
    yz
    1.34
    86
    1.09
    xxxxxxxx
    1.08
    peria
    1.07
    anth
    1.05
    ylene
    1.04
    posed
    1.03
    avier
    1.03
    eno
    1.02
    aml
    0.99
    Act Density 0.016%

    No Known Activations