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

    Neuronpedia

    INDEX
    Explanations

    positive expressions of sentiment or reinforcement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     or
    -0.15
     pis
    -0.15
     sheer
    -0.14
    rick
    -0.14
    isis
    -0.13
    isma
    -0.13
    ÙĪج
    -0.13
    zsche
    -0.13
     Julius
    -0.13
    orsi
    -0.13
    POSITIVE LOGITS
    igu
    0.15
    âķĹ
    0.15
    .DropDown
    0.15
    /WebAPI
    0.14
    oten
    0.14
    udo
    0.14
    ayette
    0.14
    OwnProperty
    0.14
    athing
    0.14
    FAULT
    0.13
    Act Density 0.019%

    No Known Activations