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

    Neuronpedia

    INDEX
    Explanations

    words related to places or positions where objects are located or activities are done

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "rest" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holes
    -0.84
    女
    -0.75
    inx
    -0.68
    hole
    -0.64
    bender
    -0.62
     Crusher
    -0.62
    shr
    -0.61
    eker
    -0.61
    xx
    -0.60
     Daredevil
    -0.59
    POSITIVE LOGITS
    oleon
    0.87
    ornia
    0.86
    eatures
    0.82
    raint
    0.80
    ricting
    0.78
    ructure
    0.78
    rete
    0.77
    dinand
    0.75
     resting
    0.73
    ouble
    0.73
    Act Density 0.017%

    No Known Activations