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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons of lower quantities or qualities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the concept of "least" or minimal comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ses
    -0.80
     Reborn
    -0.76
    xxxxxxxx
    -0.72
    kefeller
    -0.72
    clerosis
    -0.69
    gnu
    -0.68
    xxxx
    -0.68
    axter
    -0.66
    kas
    -0.66
    kan
    -0.65
    POSITIVE LOGITS
    erest
    0.80
     practicable
    0.75
     bit
    0.75
     intrusive
    0.74
     toler
    0.72
     possible
    0.71
     conspicuous
    0.70
     conceivable
    0.69
     amount
    0.69
     forgiving
    0.68
    Act Density 0.016%

    No Known Activations