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

    Neuronpedia

    INDEX
    Explanations

    expressions of acknowledgment or confession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vite
    -0.16
    ibar
    -0.15
    еж
    -0.15
    Ñĩи
    -0.15
    omm
    -0.14
    issing
    -0.14
    /player
    -0.14
    347
    -0.14
    uos
    -0.14
    mares
    -0.14
    POSITIVE LOGITS
     defeat
    0.23
     to
    0.18
     having
    0.18
     truth
    0.17
     receipt
    0.16
     comp
    0.15
     responsibility
    0.15
     parts
    0.15
     mas
    0.15
    /conf
    0.15
    Act Density 0.025%

    No Known Activations