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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inet
    -0.18
     Fare
    -0.17
    eters
    -0.16
    illac
    -0.15
     ens
    -0.15
    equip
    -0.15
    ilon
    -0.14
    eter
    -0.14
    nick
    -0.14
    ving
    -0.14
    POSITIVE LOGITS
     kli
    0.16
    CPP
    0.15
     restau
    0.14
     Osborne
    0.14
    ضÛĮ
    0.14
    ìŀ¬
    0.14
    stal
    0.14
    ollen
    0.14
     tempted
    0.14
     tempt
    0.14
    Act Density 0.012%

    No Known Activations