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

    Neuronpedia

    INDEX
    Explanations

    mentions of severe damage or limitations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "severely" indicating significant negative impacts or damage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ioch
    -0.74
    akeru
    -0.73
    eer
    -0.71
    yl
    -0.71
    amide
    -0.71
    ynthesis
    -0.69
    tein
    -0.69
    atu
    -0.68
    itu
    -0.68
    iens
    -0.67
    POSITIVE LOGITS
     retarded
    0.83
     differentiated
    0.82
     severely
    0.82
     deteriorated
    0.79
     punished
    0.78
    locked
    0.77
     disabled
    0.76
     overweight
    0.76
     deterior
    0.75
     underestimate
    0.75
    Act Density 0.016%

    No Known Activations