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

    Neuronpedia

    INDEX
    Explanations

    terms related to ranking and order

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kohdetta
    -0.71
    ITTEN
    -0.69
    coaster
    -0.68
     aceptas
    -0.68
     PLW
    -0.68
    ]();
    -0.67
     Drog
    -0.66
    rigu
    -0.65
    fores
    -0.65
     _('
    -0.65
    POSITIVE LOGITS
     RANK
    2.08
     rank
    1.98
     ranks
    1.92
     Rank
    1.90
    rank
    1.88
    Rank
    1.85
     Ranks
    1.81
    RANK
    1.80
     ranking
    1.78
    ranks
    1.64
    Act Density 0.106%

    No Known Activations