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

    Neuronpedia

    INDEX
    Explanations

    negative results or outcomes in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jump
    -0.50
     ujedno
    -0.48
    Jump
    -0.47
     Sherman
    -0.46
     ſte
    -0.46
    attendre
    -0.46
     cứ
    -0.45
    Trade
    -0.45
     Houſe
    -0.45
    Storm
    -0.44
    POSITIVE LOGITS
    ArrowToggle
    0.90
    MessageOf
    0.88
     ProtoMessage
    0.82
    0.80
    AddTagHelper
    0.79
     propOrder
    0.78
    ScopeManager
    0.75
    MessageTagHelper
    0.70
    /*
    0.69
    WaitGroup
    0.69
    Act Density 0.788%

    No Known Activations