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

    Neuronpedia

    INDEX
    Explanations

    descriptions of technical specifications related to rear components

    oai_token-act-pair · gpt-3.5-turbo

    references to the "rear" part of an object or device

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensable
    -0.85
    âĸĪâĸĪ
    -0.84
    ittee
    -0.82
    Cola
    -0.76
    achu
    -0.75
    apo
    -0.74
    esson
    -0.73
    etti
    -0.72
    âĸĪâĸĪâĸĪâĸĪ
    -0.72
    utra
    -0.72
    POSITIVE LOGITS
    ward
    1.23
     axle
    1.02
    wards
    0.92
     tyre
    0.92
     derail
    0.91
    bone
    0.89
    wash
    0.85
    side
    0.85
     lobe
    0.84
    most
    0.83
    Act Density 0.009%

    No Known Activations