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

    Neuronpedia

    INDEX
    Explanations

    the word "always" and its various forms in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "always"

    np_acts-logits-general · gemini-2.0-flash

    always

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scoper
    -0.38
     organization
    -0.36
     rencontres
    -0.36
    ऽ
    -0.36
    fören
    -0.35
     compilation
    -0.35
    subpackage
    -0.35
    sstelle
    -0.34
     hende
    -0.34
    upyter
    -0.33
    POSITIVE LOGITS
    always
    1.23
    Always
    1.23
     Always
    1.21
     ALWAYS
    1.15
     always
    1.13
    ALWAYS
    1.09
     Siempre
    0.97
     alway
    0.96
    siempre
    0.96
    Siempre
    0.93
    Act Density 0.049%

    No Known Activations