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

    Neuronpedia

    INDEX
    Explanations

    words related to recordings or audio files

    oai_token-act-pair · gpt-3.5-turbo

    references to recordings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adin
    -0.83
    mere
    -0.75
    hips
    -0.71
    vier
    -0.71
    hiro
    -0.68
    kie
    -0.68
    undai
    -0.67
    ggles
    -0.66
    dh
    -0.64
    axies
    -0.64
    POSITIVE LOGITS
     recordings
    1.11
     recorder
    0.95
     recording
    0.94
     sessions
    0.93
     tapes
    0.92
    recorded
    0.92
    audio
    0.85
     microphones
    0.83
     taped
    0.80
     Recording
    0.80
    Act Density 0.015%

    No Known Activations