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

    Neuronpedia

    INDEX
    Explanations

    phrases related to limitations and disclaimers in legal or policy contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    836
    -0.18
    lege
    -0.16
    orta
    -0.15
    autor
    -0.14
    oley
    -0.14
    509
    -0.14
     Blasio
    -0.14
    ामन
    -0.14
    issance
    -0.14
    _capability
    -0.13
    POSITIVE LOGITS
    Ĥæķ°
    0.18
    pagen
    0.15
     sal
    0.14
     span
    0.14
    PageIndex
    0.14
     moz
    0.13
    .volley
    0.13
    isia
    0.13
    adera
    0.13
     Ship
    0.13
    Act Density 0.005%

    No Known Activations