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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to numerical data and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ³
    -0.17
    LETTE
    -0.16
     equiv
    -0.15
     scrut
    -0.15
     Lorenzo
    -0.15
    sla
    -0.14
     Ub
    -0.14
    STREAM
    -0.14
    _HDR
    -0.14
    382
    -0.13
    POSITIVE LOGITS
     Romanian
    0.29
     Romania
    0.27
    Äĥ
    0.23
     Buch
    0.21
     Buna
    0.19
    Roman
    0.19
    ÈĽ
    0.18
    ului
    0.18
    .ro
    0.17
    fel
    0.17
    Act Density 0.201%

    No Known Activations