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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals and things within casual or narrative conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ASY
    -0.15
     Performing
    -0.15
    ÑģÑĸм
    -0.15
    aska
    -0.14
    uese
    -0.14
    ASK
    -0.14
     classic
    -0.14
    .Model
    -0.14
    sak
    -0.14
    isco
    -0.13
    POSITIVE LOGITS
     thing
    0.27
     stuff
    0.24
    thing
    0.23
     Stuff
    0.20
     Thing
    0.20
     guy
    0.18
    stuff
    0.18
    MUX
    0.17
    (thing
    0.16
    zenÃŃ
    0.16
    Act Density 0.128%

    No Known Activations