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

    Neuronpedia

    INDEX
    Explanations

    terms related to strictness or rigidity in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Oates
    -0.80
     Vella
    -0.76
     possibili
    -0.75
     Myster
    -0.73
    inazione
    -0.71
    الحياه
    -0.70
    pel
    -0.69
    Sey
    -0.68
     AUSSI
    -0.68
     Caron
    -0.67
    POSITIVE LOGITS
     strict
    1.09
     tight
    1.02
    Tight
    0.99
    tight
    0.93
     Tight
    0.89
     Strict
    0.85
     tightened
    0.83
    "):
    0.83
     rígido
    0.81
     estric
    0.80
    Act Density 0.148%

    No Known Activations