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

    Neuronpedia

    INDEX
    Explanations

    attributes of programming constructs, particularly related to class definitions and variable modifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onom
    -0.19
    chter
    -0.16
     èĤ
    -0.16
    ÏĥÏĦα
    -0.15
    onic
    -0.15
    lette
    -0.15
    agma
    -0.14
    ÌĤ
    -0.14
    ách
    -0.14
    ä¼ij
    -0.14
    POSITIVE LOGITS
    odus
    0.17
    .metamodel
    0.16
     Bale
    0.15
    dehyde
    0.15
     Kaplan
    0.15
    782
    0.14
    resher
    0.14
     Shirt
    0.14
    uentes
    0.14
    uger
    0.14
    Act Density 0.003%

    No Known Activations