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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names within the text

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

    instances of the word "Name" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (""));
    -0.52
    )++;
    -0.52
    ArrowToggle
    -0.50
     Schwar
    -0.49
    viously
    -0.48
     suced
    -0.47
    latego
    -0.47
     fleeing
    -0.46
     السكان
    -0.45
    jø
    -0.45
    POSITIVE LOGITS
    Name
    1.77
     Name
    1.48
    name
    1.23
     name
    1.21
     NAME
    1.15
    NAME
    1.11
     ModelExpression
    1.02
     كومونز
    1.01
     AssemblyTitle
    0.99
     Names
    0.95
    Act Density 0.017%

    No Known Activations