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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "fine" in different contexts

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

    "fine" and its related contexts

    np_acts-logits-general · gemini-2.0-flash

    fine print, dining, tuning, particles, cut

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rrggbb
    -0.53
    Cyfeiriadau
    -0.53
    ècie
    -0.52
     cesar
    -0.49
     culoare
    -0.49
    yntaxException
    -0.49
     AppColors
    -0.49
    ypsies
    -0.47
    richtig
    -0.47
     portefeuille
    -0.47
    POSITIVE LOGITS
    Fine
    1.30
     fine
    1.29
     FINE
    1.29
     Fine
    1.27
    fine
    1.25
    FINE
    1.22
     Fines
    1.05
     tuning
    1.00
     grained
    1.00
     tuned
    0.98
    Act Density 0.079%

    No Known Activations