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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "well" and its variations indicating quality and approval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Schaefer
    -0.84
     DiCaprio
    -0.72
     Nugent
    -0.70
     Lehrer
    -0.69
     McCann
    -0.68
    cifix
    -0.68
     Flug
    -0.68
     Schäfer
    -0.67
    ობ
    -0.67
     britann
    -0.66
    POSITIVE LOGITS
     well
    1.75
     WELL
    1.67
     Well
    1.63
    Well
    1.61
    well
    1.60
     wells
    1.43
    WELL
    1.37
     Wells
    1.34
    Wells
    1.34
     Welles
    1.29
    Act Density 0.077%

    No Known Activations