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

    Neuronpedia

    INDEX
    Explanations

    terms related to biological characteristics and classification methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amic
    -0.52
    épend
    -0.48
    fellow
    -0.45
    dotenv
    -0.45
     rueda
    -0.45
     aján
    -0.43
    OuterClass
    -0.42
    DUR
    -0.42
    hadap
    -0.42
     besz
    -0.42
    POSITIVE LOGITS
     distinguishing
    1.43
     differentiating
    1.26
     distinguish
    1.25
     characteristic
    1.25
     distinguishes
    1.23
     Characteristic
    1.17
     differentiates
    1.15
     differentiate
    1.12
     distinctive
    1.11
     distin
    1.11
    Act Density 0.774%

    No Known Activations