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

    Neuronpedia

    INDEX
    Explanations

    the word "just" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.87
     Efq
    -0.85
    rungsseite
    -0.83
     Reſ
    -0.79
    jspx
    -0.78
    ſelf
    -0.77
     Majefty
    -0.76
     Jefus
    -0.75
    ſelves
    -0.74
    aarrggbb
    -0.73
    POSITIVE LOGITS
     like
    0.87
     barely
    0.67
     simply
    0.64
     enough
    0.63
     plain
    0.63
     before
    0.62
     as
    0.62
     about
    0.58
     zoals
    0.54
     such
    0.54
    Act Density 0.069%

    No Known Activations