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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the act of revealing or disclosing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SSIP
    -0.17
    hei
    -0.16
    ATAB
    -0.15
    /devices
    -0.15
    η
    -0.15
    ilon
    -0.15
    Accessor
    -0.15
    -Ñħ
    -0.14
    quets
    -0.14
    rena
    -0.14
    POSITIVE LOGITS
    iveness
    0.17
    ance
    0.17
    ively
    0.16
    rack
    0.16
    mente
    0.16
    931
    0.15
    tog
    0.15
    iance
    0.15
    odable
    0.15
    aries
    0.14
    Act Density 0.049%

    No Known Activations