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

    Neuronpedia

    INDEX
    Explanations

    identifications and experiences related to surprise and discovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ole
    -0.15
    Æ°ng
    -0.14
    assin
    -0.14
    indle
    -0.14
    InSection
    -0.13
    ingham
    -0.13
     actual
    -0.13
     mentioned
    -0.13
     display
    -0.13
     赤
    -0.13
    POSITIVE LOGITS
     fucks
    0.16
     otherwise
    0.16
     fucked
    0.15
    azzi
    0.15
    iske
    0.15
     aprove
    0.15
    enson
    0.14
    GENCY
    0.14
     neither
    0.14
     invent
    0.14
    Act Density 0.060%

    No Known Activations