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

    Neuronpedia

    INDEX
    Explanations

    terms related to computer science and technology, particularly those associated with security and machine learning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á»ģn
    -0.20
    _subtype
    -0.15
    oard
    -0.15
    reator
    -0.15
    orian
    -0.15
    precated
    -0.15
    igers
    -0.14
    .subtract
    -0.14
    vara
    -0.14
    Uvs
    -0.14
    POSITIVE LOGITS
    arial
    0.18
    illi
    0.15
    irm
    0.15
     ngOnInit
    0.15
     Vive
    0.14
     dame
    0.14
    933
    0.14
    ech
    0.14
     Cock
    0.14
    nel
    0.14
    Act Density 0.030%

    No Known Activations