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

    Neuronpedia

    INDEX
    Explanations

    the word "always" in various forms and contexts

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

    always or ever

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tiro
    -0.35
     The
    -0.33
    Со
    -0.33
     various
    -0.33
    S
    -0.33
    T
    -0.32
    c
    -0.32
     His
    -0.32
    Entered
    -0.32
     T
    -0.32
    POSITIVE LOGITS
     always
    0.87
     תמיד
    0.83
     ALWAYS
    0.83
    always
    0.82
     siempre
    0.82
    Always
    0.79
    Personendaten
    0.77
     selalu
    0.77
     Always
    0.76
    LookAnd
    0.76
    Act Density 0.014%

    No Known Activations