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

    Neuronpedia

    INDEX
    Explanations

    references to specific geographical locations and organizational terms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    URDAY
    -0.57
    dire
    -0.51
     SONS
    -0.50
     Diman
    -0.49
     Itself
    -0.49
     inclusions
    -0.48
     jugement
    -0.47
    }}"
    -0.47
     stesse
    -0.47
     Moussa
    -0.47
    POSITIVE LOGITS
    uxxxx
    0.77
     usually
    0.70
     referrerpolicy
    0.70
     ModelExpression
    0.65
    Usually
    0.63
    usually
    0.63
    Rptr
    0.62
    NameInMap
    0.62
    RunAsync
    0.61
     often
    0.60
    Act Density 0.225%

    No Known Activations