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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to numerical values and thresholds in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bryant
    -0.15
    бол
    -0.15
     Ãľst
    -0.14
    ebi
    -0.14
    utto
    -0.14
    .vertx
    -0.14
     rand
    -0.14
     espect
    -0.14
    oser
    -0.13
    eddar
    -0.13
    POSITIVE LOGITS
    823
    0.16
    pheric
    0.15
     prostitu
    0.15
    114
    0.14
    phere
    0.14
    acula
    0.14
    923
    0.14
    074
    0.13
    zbollah
    0.13
    phem
    0.13
    Act Density 0.002%

    No Known Activations