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

    Neuronpedia

    INDEX
    Explanations

    terms related to unintended events and accidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gnore
    -0.15
    erchant
    -0.15
    /sm
    -0.15
    Ùıر
    -0.15
    нина
    -0.15
    ndata
    -0.14
    Äįe
    -0.14
    ODULE
    -0.14
    emory
    -0.14
    ESSAGE
    -0.14
    POSITIVE LOGITS
    aneously
    0.27
    ely
    0.23
    /random
    0.21
    ously
    0.21
    aly
    0.20
    elyn
    0.18
    DEX
    0.18
    ly
    0.18
    mente
    0.18
    ably
    0.17
    Act Density 0.075%

    No Known Activations