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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe rationality or logic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rio
    -0.18
     sharedInstance
    -0.18
    cko
    -0.16
    èĭĹ
    -0.16
    ots
    -0.15
     INCIDENTAL
    -0.15
    itez
    -0.15
    edl
    -0.15
    ijken
    -0.14
    _Impl
    -0.14
    POSITIVE LOGITS
     logical
    0.19
     logic
    0.17
    logic
    0.17
    éĢ
    0.17
    nar
    0.16
     Logical
    0.16
    arg
    0.15
    Logical
    0.15
    erral
    0.15
    fully
    0.14
    Act Density 0.014%

    No Known Activations