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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to the concept of proving or providing evidence

    oai_token-act-pair · gpt-3.5-turbo

    variations of the verb "prove."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffffcc
    -0.74
     externalToEVAOnly
    -0.72
    ummer
    -0.71
    ufact
    -0.70
     Osc
    -0.69
    catentry
    -0.68
    option
    -0.65
    vantage
    -0.64
     RIS
    -0.63
     liner
    -0.61
    POSITIVE LOGITS
     proofs
    0.77
     proof
    0.75
     authenticity
    0.74
     oneself
    0.72
    worthiness
    0.72
     innocence
    0.71
    proof
    0.71
     dispro
    0.70
    gery
    0.68
    rers
    0.68
    Act Density 0.052%

    No Known Activations