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

    Neuronpedia

    INDEX
    Explanations

    references to wings or wing-like structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wib
    -0.84
     resourceCulture
    -0.84
    extAlignment
    -0.79
    jgl
    -0.77
    cipar
    -0.75
    awtextra
    -0.73
     saites
    -0.70
    发表于
    -0.68
    ్రామ
    -0.67
    jsii
    -0.67
    POSITIVE LOGITS
     wings
    1.05
     wing
    0.96
     Wings
    0.94
     Wing
    0.86
     valves
    0.86
    Wing
    0.82
     sauces
    0.81
    pillow
    0.81
     Valves
    0.81
    Wings
    0.79
    Act Density 0.073%

    No Known Activations