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

    Neuronpedia

    INDEX
    Explanations

    references to changes in leadership or transitions in roles

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

    Tokens related to replacing or substituting

    np_acts-logits-general · gemini-2.0-flash

    replacement by someone or something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yorsunuz
    -0.35
    pexpr
    -0.35
    Personensuche
    -0.34
    oneofs
    -0.33
     المحت
    -0.32
    mmas
    -0.32
     megh
    -0.31
     shared
    -0.30
     Ogre
    -0.30
     beacon
    -0.29
    POSITIVE LOGITS
     replacements
    0.71
     replacement
    0.66
    replacement
    0.65
     substitutes
    0.62
     Replacement
    0.60
    Replacement
    0.59
    Replace
    0.58
     Replace
    0.55
     replacing
    0.55
     substituting
    0.53
    Act Density 0.333%

    No Known Activations