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

    Neuronpedia

    INDEX
    Explanations

    specific terms and their usage within a text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     convain
    -0.51
    uxxxx
    -0.49
    __(/*!
    -0.48
     météoro
    -0.48
     called
    -0.48
    šč
    -0.47
     strani
    -0.47
    :
    -0.47
     például
    -0.47
     simply
    -0.46
    POSITIVE LOGITS
    脚注の使い方
    0.91
    ScopeManager
    0.89
    StructEnd
    0.83
    IntoConstraints
    0.83
     leaſt
    0.81
     MenuView
    0.77
     ſtre
    0.77
    ThroughAttribute
    0.77
    AnchorStyles
    0.76
     raiſ
    0.75
    Act Density 0.013%

    No Known Activations