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

    Neuronpedia

    INDEX
    Explanations

    references to flat surfaces or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PMailer
    -0.90
    Życiorys
    -0.84
     CreateTagHelper
    -0.83
     StringTokenizer
    -0.82
    CodedInputStream
    -0.82
    gaben
    -0.78
     HasFactory
    -0.78
     FetchType
    -0.78
    MeasureSpec
    -0.78
    PhysRev
    -0.76
    POSITIVE LOGITS
     flat
    2.55
     Flat
    2.47
    flat
    2.36
    Flat
    2.32
     FLAT
    2.28
    FLAT
    2.15
     flats
    2.02
     Flats
    1.83
    flats
    1.73
     flattened
    1.50
    Act Density 0.034%

    No Known Activations