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

    Neuronpedia

    INDEX
    Explanations

    negative numerical ranges or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.89
    setVerticalGroup
    -0.87
    دانشنامهٔ
    -0.81
    rawDesc
    -0.81
    rungsseite
    -0.76
    awtextra
    -0.76
    MessageTagHelper
    -0.76
    addContainerGap
    -0.72
    FieldNumber
    -0.72
    })->
    -0.72
    POSITIVE LOGITS
    tvguidetime
    0.56
     åren
    0.56
     attendre
    0.56
     préfère
    0.55
     letech
    0.55
     aikana
    0.54
     Police
    0.53
     årene
    0.52
     mourir
    0.50
     laikā
    0.49
    Act Density 0.067%

    No Known Activations