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

    Neuronpedia

    INDEX
    Explanations

    future tense or modal verbs indicating intention or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LabelTagHelper
    -0.42
    Portail
    -0.41
    淘
    -0.40
    始めた
    -0.39
     помню
    -0.38
    が悪い
    -0.38
     دیکھیے
    -0.38
    Personendaten
    -0.37
    자인
    -0.37
     ***!
    -0.37
    POSITIVE LOGITS
     will
    1.85
     akan
    1.59
     sẽ
    1.58
    will
    1.52
     shall
    1.42
     zullen
    1.41
    จะ
    1.33
     będzie
    1.32
     будет
    1.30
     bude
    1.29
    Act Density 0.368%

    No Known Activations