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

    Neuronpedia

    INDEX
    Explanations

    references to tape or tape-related concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to tape recordings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ationally
    -0.68
    姫
    -0.63
    lein
    -0.63
    ancial
    -0.63
     philanthrop
    -0.61
    imov
    -0.60
     Alonso
    -0.60
     unpre
    -0.60
    abad
    -0.60
    Ĭ±
    -0.58
    POSITIVE LOGITS
     recorder
    1.21
     tapes
    1.01
     tape
    1.00
    red
    0.99
     Tape
    0.98
     cassette
    0.94
     recordings
    0.94
    clip
    0.88
    recorded
    0.87
     taped
    0.84
    Act Density 0.028%

    No Known Activations