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

    Neuronpedia

    INDEX
    Explanations

    the letter 'r' followed by another specific letter sequence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'r'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terson
    -0.74
     GOODMAN
    -0.74
     Isles
    -0.72
     Fargo
    -0.68
     compe
    -0.67
     Lobby
    -0.67
     Nieto
    -0.65
     Spartan
    -0.65
     Sons
    -0.65
    renheit
    -0.64
    POSITIVE LOGITS
    umbling
    1.23
    ipples
    1.21
    umbled
    1.18
    acking
    1.17
    ascal
    1.16
    angers
    1.16
    ipp
    1.15
    attle
    1.15
    iddles
    1.15
    ussia
    1.14
    Act Density 0.022%

    No Known Activations