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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of 'out'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    frei
    -0.17
    ervo
    -0.17
    atrix
    -0.16
    rowse
    -0.15
    atures
    -0.15
    fault
    -0.15
    berra
    -0.15
    /=
    -0.15
    prs
    -0.15
    usters
    -0.14
    POSITIVE LOGITS
    wards
    0.21
    lying
    0.19
    land
    0.19
    ta
    0.18
    ted
    0.18
    sert
    0.18
    ting
    0.17
    -of
    0.17
    tag
    0.17
    ttp
    0.16
    Act Density 0.182%

    No Known Activations