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

    Neuronpedia

    INDEX
    Explanations

    references to legal rules and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reform
    -0.15
    SSION
    -0.15
     Reform
    -0.14
    ãĥ¥
    -0.14
     reforms
    -0.14
    Insensitive
    -0.14
     norm
    -0.14
    شتÙĩ
    -0.14
    ula
    -0.13
    ixin
    -0.13
    POSITIVE LOGITS
     suspension
    0.23
     Suspension
    0.22
     invocation
    0.20
     emergency
    0.20
     invoking
    0.19
     invoke
    0.19
    Susp
    0.19
     susp
    0.19
     temporary
    0.18
     Declaration
    0.18
    Act Density 0.026%

    No Known Activations