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

    Neuronpedia

    INDEX
    Explanations

    references to historical theater and playwrights, particularly William Shakespeare

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

    Follows common words or punctuation

    np_acts-logits-general · gemini-2.0-flash

    words ending in ally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -1.13
     itſelf
    -1.10
    ſelf
    -0.99
     Jefus
    -0.98
     pleaſure
    -0.97
    ſelves
    -0.96
     poffe
    -0.95
     faſt
    -0.94
     Majefty
    -0.93
     themſelves
    -0.92
    POSITIVE LOGITS
     geven
    0.58
    makeConstraints
    0.52
    jsdelivr
    0.49
     balles
    0.45
    )=>{
    0.44
     meer
    0.44
    quinas
    0.43
     makeStyles
    0.43
    eningen
    0.43
    نه
    0.42
    Act Density 0.068%

    No Known Activations