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

    Neuronpedia

    INDEX
    Explanations

    references to experimental setups and their results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ?
    -0.63
    GEBURTSDATUM
    -0.58
    Viitteet
    -0.54
    Билгалдахарш
    -0.54
    ?"
    -0.53
    VOA
    -0.53
    canestro
    -0.49
    ukone
    -0.49
    enumii
    -0.48
    ubov
    -0.47
    POSITIVE LOGITS
     Figure
    2.42
     Fig
    2.30
    Figure
    2.29
    Fig
    2.19
    FIGURE
    1.79
     Figs
    1.79
     Figura
    1.77
     figure
    1.77
     FIGURE
    1.76
    figure
    1.73
    Act Density 2.439%

    No Known Activations