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

    Neuronpedia

    INDEX
    Explanations

    pronouns and expressions of affection or related emotional sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iastical
    -0.76
     PropTypes
    -0.73
     šir
    -0.70
     Edelman
    -0.69
     namanya
    -0.69
    esModule
    -0.67
    propTypes
    -0.67
    ★☆
    -0.67
     Toulon
    -0.66
     Meeres
    -0.66
    POSITIVE LOGITS
     with
    0.99
    zarchiwizowane
    0.74
    发表于
    0.69
    toJSONString
    0.69
     ứng
    0.68
    flink
    0.68
    μφωνα
    0.67
     preocupação
    0.67
     tampering
    0.67
     acordo
    0.66
    Act Density 0.394%

    No Known Activations