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

    Neuronpedia

    INDEX
    Explanations

    common pronouns and determiners used in statements

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

    a noun phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fubject
    -0.65
    WithIOException
    -0.64
     myſelf
    -0.60
     chofe
    -0.58
     $_"
    -0.57
     تانيه
    -0.57
     ſta
    -0.55
     <>",
    -0.55
    ſelves
    -0.55
     ſind
    -0.55
    POSITIVE LOGITS
     and
    0.41
     itself
    0.40
     is
    0.38
    et
    0.37
     widers
    0.35
     it
    0.34
     Freder
    0.34
    jarse
    0.34
     Lauderdale
    0.33
    CONTRIBUT
    0.33
    Act Density 0.086%

    No Known Activations