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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate decision-making or conditions related to choices

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    chowa
    -0.57
     thrombosis
    -0.55
     compactness
    -0.54
    ırken
    -0.54
     Rostock
    -0.53
     stessa
    -0.51
     amanecer
    -0.51
     mesmas
    -0.50
     isomorphism
    -0.50
    Aix
    -0.50
    POSITIVE LOGITS
    :✨
    0.75
     GenerationType
    0.62
     мәкал
    0.61
     الحره
    0.60
    WebControls
    0.60
    RenderAtEndOf
    0.58
    Rüyada
    0.57
    LabelTagHelper
    0.56
     '\\;'
    0.56
     nvm
    0.55
    Act Density 0.436%

    No Known Activations