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

    Neuronpedia

    INDEX
    Explanations

    the word "just" in various contexts

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

    "just"

    np_acts-logits-general · gemini-2.0-flash

    just followed by modifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.89
     Efq
    -0.87
    ſelf
    -0.85
     Majefty
    -0.82
    ſelves
    -0.80
     Reſ
    -0.80
    LookAnd
    -0.79
    jspx
    -0.77
     Diſ
    -0.74
     Jefus
    -0.72
    POSITIVE LOGITS
     plain
    0.78
     like
    0.70
     barely
    0.62
     recently
    0.57
     so
    0.55
     such
    0.54
     kidding
    0.53
     enough
    0.53
     about
    0.52
    单纯
    0.52
    Act Density 0.091%

    No Known Activations