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

    Neuronpedia

    INDEX
    Explanations

    phrases or clauses starting with "to" indicating purpose or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.79
    enumii
    -0.67
    ();)
    -0.62
     تانيه
    -0.61
     Phaser
    -0.61
     Superhost
    -0.60
     onlyOwner
    -0.59
    ŚĆ
    -0.59
     Italij
    -0.58
    uxxxx
    -0.57
    POSITIVE LOGITS
    According
    1.12
     according
    1.12
    Según
    1.12
     ifølge
    1.09
     According
    1.07
    according
    1.06
     Según
    1.05
    Selon
    1.04
     Secondo
    1.02
     Selon
    1.00
    Act Density 0.093%

    No Known Activations