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

    Neuronpedia

    INDEX
    Explanations

    expressions related to personal experiences and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     themselves
    -0.68
    กัน
    -0.66
     us
    -0.58
    themselves
    -0.56
    Portail
    -0.54
    )}}{
    -0.51
    
    -0.50
    idespread
    -0.48
     bedoeld
    -0.48
     nhau
    -0.47
    POSITIVE LOGITS
     myself
    1.33
    myself
    1.05
     Myself
    1.05
     personally
    0.92
     myſelf
    0.83
     my
    0.77
     meus
    0.74
     persönlich
    0.71
     moje
    0.71
     mijn
    0.70
    Act Density 0.384%

    No Known Activations