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

    Neuronpedia

    INDEX
    Explanations

    terms related to estimation and measurement processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    setopt
    -0.78
     Folge
    -0.77
     getRule
    -0.72
     коробка
    -0.71
    دیگر
    -0.70
     flesta
    -0.69
     Hornets
    -0.68
     Ruh
    -0.68
    konomi
    -0.67
    ্ন
    -0.67
    POSITIVE LOGITS
    ting
    1.33
    ating
    1.29
    ging
    1.27
    izing
    1.23
    NING
    1.20
    cting
    1.16
    TING
    1.15
    ning
    1.15
    zing
    1.13
    ming
    1.11
    Act Density 1.678%

    No Known Activations