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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BoxDecoration
    -0.74
    CGRectMake
    -0.62
    ANTLR
    -0.61
    XmlAccessType
    -0.59
    JoinColumn
    -0.58
    География
    -0.57
     SafeMath
    -0.57
    ybė
    -0.57
    udesta
    -0.55
    migrationBuilder
    -0.55
    POSITIVE LOGITS
    elemField
    0.58
    beca
    0.55
    ########.
    0.53
    Resposta
    0.53
    发表于
    0.52
    portlet
    0.51
     Fø
    0.51
    vikle
    0.50
     thinking
    0.48
    κλη
    0.48
    Act Density 0.175%

    No Known Activations