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

    Neuronpedia

    INDEX
    Explanations

    specific phrases or sequences indicating political or social commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    出版年
    -0.79
    __(/*!
    -0.78
    AndEndTag
    -0.70
    Chham
    -0.70
    IBOutlet
    -0.69
    StructEnd
    -0.69
    Tikang
    -0.68
    yntaxException
    -0.67
     TimeUnit
    -0.65
     lastName
    -0.65
    POSITIVE LOGITS
     protoimpl
    0.59
    省市镇
    0.48
    prüche
    0.43
    MigrationBuilder
    0.42
    <bos>
    0.42
    it
    0.42
    LookAnd
    0.40
    ţilor
    0.40
    ţi
    0.40
    かって
    0.40
    Act Density 0.060%

    No Known Activations