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

    Neuronpedia

    INDEX
    Explanations

    references to legal agreements and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akis
    -0.19
    iddet
    -0.17
    au
    -0.16
    atic
    -0.14
    Raises
    -0.14
    Į
    -0.14
    opoulos
    -0.14
    ascript
    -0.14
    .AF
    -0.14
    Argb
    -0.14
    POSITIVE LOGITS
     PCA
    0.35
    CCA
    0.34
    SPA
    0.34
    PCA
    0.33
     CSA
    0.32
     TSA
    0.31
     SSA
    0.31
    DSA
    0.30
    CAA
    0.30
    ISA
    0.30
    Act Density 0.046%

    No Known Activations