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

    Neuronpedia

    INDEX
    Explanations

    concepts related to legal obligations and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĭ
    -0.15
     ç½
    -0.15
    çĿĢ
    -0.15
    uards
    -0.15
    .mit
    -0.14
    ÌĤ
    -0.14
    cloak
    -0.14
    ôi
    -0.13
    .snp
    -0.13
     beg
    -0.13
    POSITIVE LOGITS
    requires
    0.19
     requires
    0.19
     odv
    0.16
     Requires
    0.15
     Must
    0.14
    ookie
    0.14
     å¿ħ
    0.14
    å¿ħé¡»
    0.14
     Äijòi
    0.14
    Must
    0.14
    Act Density 0.076%

    No Known Activations