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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences where something is lacking or missing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "no."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RAFT
    -0.71
    midt
    -0.66
    ean
    -0.66
    mire
    -0.65
    lus
    -0.64
    thouse
    -0.63
    rex
    -0.62
    aly
    -0.62
    nesium
    -0.62
    inarily
    -0.60
    POSITIVE LOGITS
    xious
    1.20
     measurable
    0.93
     meaningful
    0.93
     detectable
    0.91
     discern
    0.90
    except
    0.89
     doubt
    0.88
     longer
    0.88
     shortage
    0.87
    onday
    0.86
    Act Density 0.095%

    No Known Activations