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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the letter "H" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -0.98
     ་་
    -0.88
     ſind
    -0.85
     verſ
    -0.84
     ſever
    -0.84
     iſt
    -0.80
     viſ
    -0.79
     Sada
    -0.76
     Tade
    -0.74
     ſhall
    -0.73
    POSITIVE LOGITS
     H
    3.06
    H
    2.66
    setH
    1.64
    rH
    1.37
    xH
    1.28
    mH
    1.24
    Ｈ
    1.24
     h
    1.21
    𝐻
    1.14
     ह
    1.13
    Act Density 0.097%

    No Known Activations