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

    Neuronpedia

    INDEX
    Explanations

    words related to academic and research-related achievements and qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TypedDataSet
    -0.56
     consumption
    -0.52
     Misch
    -0.52
     shop
    -0.51
    querySelector
    -0.50
     AttributeSet
    -0.49
     CONSUM
    -0.48
    schw
    -0.48
     shopping
    -0.48
    Psycho
    -0.48
    POSITIVE LOGITS
     colleagues
    0.73
     Walkover
    0.72
    research
    0.71
     research
    0.71
     Colleagues
    0.71
    parsedMessage
    0.65
     colleague
    0.64
    faculty
    0.62
     researchers
    0.61
    doctoral
    0.61
    Act Density 0.948%

    No Known Activations