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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "hi" in varying frequencies

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

    greeting "hi"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orianCalendar
    -0.51
    arat
    -0.51
    textTheme
    -0.51
    Erstellt
    -0.50
    onov
    -0.49
    orar
    -0.46
    onus
    -0.46
    Programme
    -0.46
     useParams
    -0.45
    beda
    -0.45
    POSITIVE LOGITS
    hi
    2.56
    HI
    1.72
    Hi
    1.59
     hi
    1.54
     Hi
    1.53
     HI
    1.42
    hiy
    1.05
    ahi
    1.01
    hii
    0.98
    hiel
    0.93
    Act Density 0.006%

    No Known Activations