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

    Neuronpedia

    INDEX
    Explanations

    terms related to recommendations and evaluations in a report or inquiry context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olk
    -0.18
    uz
    -0.16
    rror
    -0.16
    allas
    -0.15
    enze
    -0.15
    legen
    -0.14
    stoff
    -0.14
    Ñĥз
    -0.14
    Ordered
    -0.14
    tica
    -0.14
    POSITIVE LOGITS
     made
    0.99
    made
    0.85
    Made
    0.77
     Made
    0.75
     MADE
    0.69
    -made
    0.66
    emade
    0.49
     Ñģдел
    0.41
     mad
    0.37
     зÑĢоб
    0.36
    Act Density 0.338%

    No Known Activations