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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence delimiters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unplayable
    -0.87
    ########.
    -0.85
    IndentedString
    -0.77
    principalColumn
    -0.76
     GenerationType
    -0.76
     weirdly
    -0.73
    ècie
    -0.72
    IntoConstraints
    -0.72
    MigrationBuilder
    -0.72
    cèse
    -0.70
    POSITIVE LOGITS
     initiatives
    0.74
     technologies
    0.64
     activities
    0.63
     products
    0.56
     opportunities
    0.56
     efforts
    0.55
     environments
    0.55
     provides
    0.55
     services
    0.55
     programs
    0.54
    Act Density 0.303%

    No Known Activations