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

    Neuronpedia

    INDEX
    Explanations

    the word "Despite" in texts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate contrast or contradiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oided
    -0.82
    ANS
    -0.73
    culated
    -0.71
    ecycle
    -0.71
    rone
    -0.70
    ribe
    -0.69
    iaries
    -0.66
    area
    -0.66
    isa
    -0.65
    irez
    -0.65
    POSITIVE LOGITS
     assurances
    1.01
     setbacks
    1.01
     appearances
    1.00
     acknowledging
    0.98
     seeming
    0.95
     being
    0.92
     having
    0.91
     boasting
    0.91
     foregoing
    0.89
     warnings
    0.88
    Act Density 0.058%

    No Known Activations