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

    Neuronpedia

    INDEX
    Explanations

    punctuation and special characters associated with names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ẩu
    -0.17
    evin
    -0.15
    .scalablytyped
    -0.15
    omik
    -0.15
    éĻµ
    -0.15
    _Runtime
    -0.15
    ÅĻi
    -0.14
     -------------------------------------------------------------------------
    -0.14
    otte
    -0.14
    ÃŃÅ¡
    -0.14
    POSITIVE LOGITS
     William
    0.31
     Thomas
    0.30
     Sir
    0.29
     John
    0.26
     Robert
    0.26
     Richard
    0.26
     Edward
    0.24
    William
    0.24
     Henry
    0.24
    Thomas
    0.24
    Act Density 0.047%

    No Known Activations