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

    Neuronpedia

    INDEX
    Explanations

    non-physical, abstract concepts related to errors and faults

    oai_token-act-pair · gpt-3.5-turbo

    references to mistakes and failures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asus
    -0.77
    owder
    -0.74
    OV
    -0.73
    ateur
    -0.71
    jet
    -0.68
    mun
    -0.66
    RA
    -0.66
    DES
    -0.66
    trak
    -0.65
    ramid
    -0.65
    POSITIVE LOGITS
    cale
    1.12
     abound
    0.98
    omething
    0.96
    pring
    0.90
    hooting
    0.88
     plag
    0.87
    cape
    0.84
    pace
    0.83
    ome
    0.83
    ":[{"
    0.81
    Act Density 0.317%

    No Known Activations