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

    Neuronpedia

    INDEX
    Explanations

    the presence and repetition of the word "a" or variations of it in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portail
    -0.65
    (@"%@",
    -0.60
    ArrowToggle
    -0.58
     Parfum
    -0.57
     Higgins
    -0.57
    fonte
    -0.56
     אחרים
    -0.54
    🔰
    -0.53
    (!__
    -0.52
    savevideo
    -0.51
    POSITIVE LOGITS
    تقاوى
    0.69
     very
    0.67
     Jot
    0.66
    ándolo
    0.66
     Preguntas
    0.66
    RetentionPolicy
    0.66
    ándola
    0.65
    JNIEnv
    0.64
    DataAnnotations
    0.63
    kháu
    0.63
    Act Density 0.289%

    No Known Activations