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

    Neuronpedia

    INDEX
    Explanations

    words that convey respect and recognition for individuals or their contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adra
    -1.03
    ascript
    -0.92
    arettes
    -0.84
    adas
    -0.81
    cise
    -0.80
    addon
    -0.78
    thia
    -0.76
    plet
    -0.75
    alion
    -0.73
    agements
    -0.73
    POSITIVE LOGITS
     scholar
    0.98
     literary
    0.97
     journalist
    0.97
     economist
    0.95
     mathematician
    0.89
     journalistic
    0.88
     historian
    0.87
     columnist
    0.87
     critic
    0.87
     physicist
    0.86
    Act Density 0.044%

    No Known Activations