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

    Neuronpedia

    INDEX
    Explanations

    possible or potential scenarios discussed in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.76
    ReusableCell
    -0.66
     Sirs
    -0.66
     BOP
    -0.63
     MainAxisSize
    -0.62
    CWE
    -0.61
     Majesty
    -0.60
     Medea
    -0.60
    =“
    -0.59
    reactstrap
    -0.59
    POSITIVE LOGITS
     conceivably
    1.11
     COULD
    0.99
     possibly
    0.98
     potentially
    0.93
     could
    0.91
     Could
    0.87
    could
    0.86
    Could
    0.85
     Possibly
    0.84
     theoretically
    0.83
    Act Density 0.103%

    No Known Activations