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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or groups identified as "fellow."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Annette
    -0.75
    Annette
    -0.74
     Sands
    -0.73
    vernight
    -0.70
    ¯¯
    -0.66
     Eras
    -0.64
     Réponses
    -0.63
     stink
    -0.63
    XXXXXXXX
    -0.63
    creas
    -0.62
    POSITIVE LOGITS
     fellow
    2.00
    Fellow
    1.99
     Fellow
    1.97
     FELLOW
    1.89
    fellow
    1.75
     Fellows
    1.58
     fellows
    1.45
     Fellowship
    1.17
     fellowship
    1.10
     fellowships
    1.04
    Act Density 0.060%

    No Known Activations