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

    Neuronpedia

    INDEX
    Explanations

    instances of negotiation or decision-making language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agas
    -0.16
    utral
    -0.15
     marque
    -0.15
    νομ
    -0.15
    ptal
    -0.15
    urnal
    -0.14
    é§Ĩ
    -0.14
     grat
    -0.14
     angel
    -0.14
    égor
    -0.14
    POSITIVE LOGITS
     Wade
    0.15
    ROLL
    0.14
    olem
    0.14
    hyp
    0.14
    Ø´Ùģ
    0.14
    elyn
    0.14
    ormsg
    0.14
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.14
    uci
    0.14
    eldon
    0.14
    Act Density 0.012%

    No Known Activations