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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases indicating states of being or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Word "is" or "are"

    np_acts-logits-general · gemini-2.0-flash

    otherwise, subsequently, previously

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     that
    -0.89
    jenige
    -0.76
     infatti
    -0.72
     StatefulWidget
    -0.70
     NSCoder
    -0.70
    .*")]
    -0.69
    Hentet
    -0.69
    AndEndTag
    -0.68
     propOrder
    -0.66
    InjectAttribute
    -0.66
    POSITIVE LOGITS
     otherwise
    0.94
     hopefully
    0.73
    otherwise
    0.71
     OTHERWISE
    0.68
     supposedly
    0.67
     hitherto
    0.66
    Otherwise
    0.65
     subsequently
    0.65
     previously
    0.65
     supposed
    0.64
    Act Density 0.383%

    No Known Activations