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

    Neuronpedia

    INDEX
    Explanations

    references to names and relationships in obituaries

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

    Preceding pronouns and capitalized words

    np_acts-logits-general · gemini-2.0-flash

    pronoun verb phrase beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Exacts
    -0.66
     сча
    -0.64
    NameInMap
    -0.53
     yet
    -0.48
    cmu
    -0.47
     inevitably
    -0.47
    Rptr
    -0.47
     Harvard
    -0.46
    bidden
    -0.46
    Yet
    -0.46
    POSITIVE LOGITS
    tonode
    0.65
    Бахар
    0.63
     כן
    0.61
    TypedDataSet
    0.60
    hyrchwyd
    0.59
    enderror
    0.59
    zbęd
    0.58
    ArgsConstructor
    0.58
    UrlResolution
    0.58
    oneofs
    0.57
    Act Density 0.058%

    No Known Activations