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

    Neuronpedia

    INDEX
    Explanations

    repeated usage of the word "always."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Muffins
    -0.84
     parís
    -0.82
     âgées
    -0.79
     bombe
    -0.78
    er
    -0.77
    Niels
    -0.74
     Lippincott
    -0.73
     Noire
    -0.72
     vnto
    -0.70
    ه
    -0.69
    POSITIVE LOGITS
     always
    1.92
     Always
    1.85
     ALWAYS
    1.77
    always
    1.77
    Always
    1.76
    ALWAYS
    1.63
     siempre
    1.30
     alway
    1.28
     Siempre
    1.26
    Siempre
    1.25
    Act Density 0.071%

    No Known Activations