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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and their relationships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Herb
    -0.17
     colon
    -0.15
     cÃł
    -0.15
     Bilim
    -0.15
    Professor
    -0.15
     hala
    -0.15
    _THROW
    -0.14
    lobber
    -0.14
    ancell
    -0.14
     downs
    -0.14
    POSITIVE LOGITS
     Connor
    0.24
    Connor
    0.20
     Brandon
    0.19
     Feder
    0.19
     Dillon
    0.18
     Brittany
    0.17
     Joshua
    0.17
     Maxim
    0.17
     Lucas
    0.17
    aign
    0.17
    Act Density 0.148%

    No Known Activations