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

    Neuronpedia

    INDEX
    Explanations

    interrogative phrases starting with "Did" or "Will"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     desmotivaciones
    -0.74
    pecabe
    -0.73
     aleación
    -0.69
     bambú
    -0.66
     exportación
    -0.66
    ientras
    -0.65
    berdayakan
    -0.64
     plufieurs
    -0.63
     manguera
    -0.63
     increí
    -0.63
    POSITIVE LOGITS
     Did
    1.19
    Did
    1.13
     did
    1.11
    did
    0.98
     DID
    0.90
     Does
    0.90
    Does
    0.80
     didn
    0.77
     does
    0.76
    ref
    0.75
    Act Density 0.835%

    No Known Activations