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

    Neuronpedia

    INDEX
    Explanations

    Amazon devices, especially those related to the Echo product line

    oai_token-act-pair · gpt-3.5-turbo

    references to Amazon Echo devices and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amins
    -0.81
    oppable
    -0.80
    alcohol
    -0.80
    ARDS
    -0.74
    udeb
    -0.73
    acca
    -0.72
    src
    -0.71
    ammad
    -0.71
    ohn
    -0.71
    cohol
    -0.70
    POSITIVE LOGITS
    piece
    0.77
     Echo
    0.77
     Chamber
    0.72
     chamber
    0.70
     mosqu
    0.69
    arthed
    0.67
    angel
    0.67
     capsule
    0.67
     chambers
    0.67
    pieces
    0.67
    Act Density 0.025%

    No Known Activations