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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antro
    -0.18
    osci
    -0.16
    jerne
    -0.16
     ë©´
    -0.16
    "';
    -0.15
    alloca
    -0.15
     Midi
    -0.15
     Pied
    -0.15
    arov
    -0.15
    infeld
    -0.14
    POSITIVE LOGITS
     Newfoundland
    0.34
     Labrador
    0.28
     Aval
    0.26
     NL
    0.23
     St
    0.23
    foundland
    0.23
     NFL
    0.22
     cod
    0.20
    rador
    0.20
    NL
    0.20
    Act Density 0.028%

    No Known Activations