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

    Neuronpedia

    INDEX
    Explanations

    mentions of nuts

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of nuts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VO
    -0.69
    Reply
    -0.67
    pless
    -0.65
     Stall
    -0.65
    nered
    -0.64
    naire
    -0.61
     Volunteers
    -0.59
     Rapp
    -0.59
    SIGN
    -0.59
    UTION
    -0.59
    POSITIVE LOGITS
     nuts
    1.15
    nuts
    0.88
    hed
    0.85
    sey
    0.84
     brittle
    0.82
    zyme
    0.81
    linger
    0.81
    seys
    0.80
     wrench
    0.79
    nut
    0.79
    Act Density 0.006%

    No Known Activations