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

    Neuronpedia

    INDEX
    Explanations

    references to external or non-standard conditions or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſeveral
    -0.88
     feveral
    -0.73
     chofe
    -0.70
     fhew
    -0.70
     fhort
    -0.70
     fometimes
    -0.69
     poffible
    -0.68
     perſon
    -0.68
     auffi
    -0.68
     reaſon
    -0.67
    POSITIVE LOGITS
    AndEndTag
    1.08
     ilman
    0.79
     without
    0.78
     ohne
    0.78
    without
    0.72
    Without
    0.70
    YOND
    0.69
    Без
    0.69
    ArrowToggle
    0.69
     без
    0.69
    Act Density 0.608%

    No Known Activations