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

    Neuronpedia

    INDEX
    Explanations

    phrases that include the term "out."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atrix
    -0.15
    atur
    -0.15
    bast
    -0.15
    kate
    -0.15
    antro
    -0.15
    lint
    -0.14
    át
    -0.14
    ÑĤÑĢо
    -0.14
    VES
    -0.14
    kin
    -0.14
    POSITIVE LOGITS
    wards
    0.22
    lying
    0.18
    ta
    0.17
    _userdata
    0.16
    liers
    0.16
     Peek
    0.16
    -of
    0.15
    ickle
    0.15
    ensively
    0.15
    land
    0.15
    Act Density 0.124%

    No Known Activations