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

    Neuronpedia

    INDEX
    Explanations

    terms indicating types of damages or liabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leich
    -0.15
    chooser
    -0.15
    729
    -0.15
    avia
    -0.14
    Authority
    -0.14
     Authority
    -0.14
    _FLAG
    -0.14
     addslashes
    -0.14
    readonly
    -0.14
    Ø®ÙĬ
    -0.13
    POSITIVE LOGITS
    ushima
    0.17
    offee
    0.16
    irl
    0.16
    anja
    0.15
     Zum
    0.15
    odb
    0.15
    oz
    0.15
    nova
    0.14
     Kin
    0.14
    dere
    0.14
    Act Density 0.000%

    No Known Activations