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

    Neuronpedia

    INDEX
    Explanations

    written or verbal references to pencils

    oai_token-act-pair · gpt-3.5-turbo

    references to writing instruments, particularly pencils

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctuary
    -0.85
    76561
    -0.82
    æĪ¦
    -0.72
    κ
    -0.71
    vict
    -0.71
    rons
    -0.70
    mit
    -0.70
    thy
    -0.69
     cele
    -0.69
    terness
    -0.69
    POSITIVE LOGITS
    etry
    0.80
    otle
    0.75
    issors
    0.75
    writer
    0.75
    wra
    0.69
     ribbon
    0.69
    ophone
    0.68
     zipper
    0.67
    wrap
    0.67
    yz
    0.66
    Act Density 0.018%

    No Known Activations