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

    Neuronpedia

    INDEX
    Explanations

    words related to ambiguous or uncertain situations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "amb."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     losers
    -0.60
    backer
    -0.59
     detectors
    -0.58
    nings
    -0.57
    kies
    -0.57
     stub
    -0.57
    TY
    -0.57
    creen
    -0.57
    naires
    -0.56
     bailed
    -0.56
    POSITIVE LOGITS
    urger
    1.09
    assador
    1.04
    uilding
    1.01
    assadors
    0.99
    olitan
    0.97
    utan
    0.96
    olin
    0.92
    olic
    0.92
    uild
    0.88
    rella
    0.88
    Act Density 0.029%

    No Known Activations