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

    Neuronpedia

    INDEX
    Explanations

    words related to emotional or qualitative states expressed as nouns, particularly those ending in "ness."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilibrium
    -0.61
     prova
    -0.58
     neutr
    -0.56
    ViewFeatures
    -0.53
    Create
    -0.52
    Def
    -0.50
    prova
    -0.50
    준
    -0.50
    Transform
    -0.50
     spieg
    -0.49
    POSITIVE LOGITS
    ⓧ
    0.93
    
    0.89
    GeoNames
    0.87
    OrNil
    0.83
    */].
    0.82
    posedge
    0.82
    0.79
     ControllerBase
    0.78
     فريبيس
    0.77
    uxxxx
    0.76
    Act Density 0.380%

    No Known Activations