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

    Neuronpedia

    INDEX
    Explanations

    phrases related to possibilities and methods of achieving goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.57
     ComVisible
    -0.56
    ivasan
    -0.54
     transférez
    -0.52
    aarrggbb
    -0.52
    ıldız
    -0.52
    ondheim
    -0.51
    principalColumn
    -0.49
    Архівовано
    -0.48
    icate
    -0.47
    POSITIVE LOGITS
     doing
    2.81
    Doing
    2.69
     Doing
    2.66
    doing
    2.34
     melakukannya
    2.22
     done
    2.12
     hacerlo
    2.12
     DOING
    2.03
     doin
    1.94
     farlo
    1.90
    Act Density 0.701%

    No Known Activations