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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons and contrasts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    soType
    -0.72
    anger
    -0.71
     href
    -0.67
    itor
    -0.65
     vigilance
    -0.64
    displayText
    -0.63
    itors
    -0.62
    illin
    -0.60
    licks
    -0.59
    estic
    -0.59
    POSITIVE LOGITS
     totals
    1.00
     TOTAL
    0.97
     total
    0.90
     pretty
    0.81
     amounted
    0.79
     Total
    0.76
     totaled
    0.75
     roughly
    0.74
     Combined
    0.72
     totaling
    0.71
    Act Density 0.354%

    No Known Activations