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

    Neuronpedia

    INDEX
    Explanations

    structured data types and their definitions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    velope
    -0.15
    idor
    -0.15
    elsea
    -0.15
    ми
    -0.14
     Sor
    -0.13
     infer
    -0.13
    efore
    -0.13
     Williamson
    -0.13
    irie
    -0.13
    оÑī
    -0.13
    POSITIVE LOGITS
    stral
    0.15
    emm
    0.15
    gang
    0.14
    anden
    0.14
     canal
    0.14
    ASA
    0.14
    ulum
    0.13
     lược
    0.13
    asu
    0.13
    amam
    0.13
    Act Density 0.008%

    No Known Activations