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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing positive outcomes or benefits related to performance expectations

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

    preceding conditions or doubts

    np_acts-logits-general · gemini-2.0-flash

    potential conditional implications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.54
     P
    -0.50
     treo
    -0.49
     Y
    -0.48
     K
    -0.48
     caros
    -0.45
     E
    -0.45
     T
    -0.45
     M
    -0.45
     W
    -0.44
    POSITIVE LOGITS
     ་་
    0.87
    addContainerGap
    0.80
     BoxFit
    0.79
    SequentialGroup
    0.77
     ―――――
    0.74
     AspNetCore
    0.70
     shouldBe
    0.69
     itſelf
    0.69
     createSlice
    0.69
    OrBuilder
    0.68
    Act Density 1.118%

    No Known Activations