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

    Neuronpedia

    INDEX
    Explanations

    versions of software

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "of" and its context within various statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agy
    -0.82
    iewicz
    -0.80
    qqa
    -0.77
    anchester
    -0.74
    uto
    -0.73
    ciplinary
    -0.71
    idad
    -0.68
    uclear
    -0.67
     chants
    -0.67
    onyms
    -0.66
    POSITIVE LOGITS
     course
    0.90
     Adren
    0.82
     FIG
    0.82
     each
    0.81
     Windows
    0.80
     Ubuntu
    0.75
     Firefox
    0.74
     Android
    0.73
     GHC
    0.72
     VERS
    0.71
    Act Density 0.253%

    No Known Activations