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

    Neuronpedia

    INDEX
    Explanations

    patterns of negative sentiment or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    long term

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    JsonInclude
    -0.50
     CURIAM
    -0.49
     CascadeType
    -0.47
    setVerticalGroup
    -0.47
     jButton
    -0.47
     cadeira
    -0.46
     AttributeSet
    -0.46
    occasione
    -0.45
     brancas
    -0.44
    principalColumn
    -0.44
    POSITIVE LOGITS
     long
    0.96
     Long
    0.93
    getLong
    0.92
    Long
    0.90
    long
    0.86
     LONG
    0.83
     Longo
    0.81
    LONG
    0.79
     longe
    0.78
     longs
    0.71
    Act Density 0.009%

    No Known Activations