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

    Neuronpedia

    INDEX
    Explanations

    phrases related to generating or producing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     already
    -0.16
    ought
    -0.16
    rd
    -0.15
    /th
    -0.15
    per
    -0.15
    rm
    -0.15
    ord
    -0.15
    ote
    -0.15
    ako
    -0.14
    iw
    -0.14
    POSITIVE LOGITS
    486
    0.19
    yš
    0.18
    ugins
    0.17
    477
    0.16
    uplic
    0.16
    ismo
    0.16
    875
    0.15
    abis
    0.14
    oftware
    0.14
    oeff
    0.14
    Act Density 0.044%

    No Known Activations