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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the initiation of an action or process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    خدام
    -0.78
     Krebs
    -0.76
     off
    -0.74
     отношению
    -0.70
     stuff
    -0.69
     Loth
    -0.68
    MathML
    -0.67
    holtz
    -0.67
     ​​
    -0.67
     Lotte
    -0.67
    POSITIVE LOGITS
     Bergman
    0.84
    Dana
    0.80
    المناصب
    0.79
    + 
    0.78
     Perseus
    0.78
     brie
    0.78
    begins
    0.78
     Beasley
    0.77
     Alat
    0.77
     piú
    0.76
    Act Density 0.086%

    No Known Activations