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

    Neuronpedia

    INDEX
    Explanations

    key terms related to laws, regulations, and official documents

    oai_token-act-pair · gpt-3.5-turbo

    different types of legislative or formal documents and proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Redd
    -0.74
    cult
    -0.70
    ZI
    -0.68
    ð
    -0.67
    ãĥ©ãĥ³
    -0.67
    Lens
    -0.63
    Unknown
    -0.63
    dden
    -0.62
    dropping
    -0.62
    sbm
    -0.61
    POSITIVE LOGITS
     consisted
    1.03
     culmin
    1.03
     consists
    1.00
     also
    0.93
     revolves
    0.91
     comprises
    0.91
     includes
    0.90
     itself
    0.82
     contains
    0.81
     relies
    0.81
    Act Density 0.275%

    No Known Activations