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

    Neuronpedia

    INDEX
    Explanations

    nouns and their corresponding grammatical constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.61
    \{\\
    -0.59
    RenderAtEndOf
    -0.58
    SerializedSize
    -0.54
    }}">
    -0.53
     Certo
    -0.53
    lungen
    -0.53
    Código
    -0.53
    WebControls
    -0.52
    /***/
    -0.51
    POSITIVE LOGITS
    Noun
    0.72
     noun
    0.72
    ArgsConstructor
    0.71
    SourceChecksum
    0.68
     nouns
    0.63
     Numerade
    0.62
     pronoun
    0.58
     Noun
    0.58
     pronouns
    0.58
    singular
    0.57
    Act Density 0.468%

    No Known Activations