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

    Neuronpedia

    INDEX
    Explanations

    references to submerged or sunken objects or structures

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    enterOuterAlt
    -0.57
     gio
    -0.54
     COUNTER
    -0.52
    batore
    -0.52
    PerformLayout
    -0.51
     AssemblyProduct
    -0.51
     counter
    -0.50
     Shower
    -0.50
    fä
    -0.49
    testify
    -0.49
    POSITIVE LOGITS
     sank
    2.67
     sinking
    2.61
     sunk
    2.59
     sunken
    1.50
     Sank
    1.40
    inking
    1.14
     sinks
    0.99
     HasFactory
    0.73
     hund
    0.71
     shipwreck
    0.67
    Act Density 0.001%

    No Known Activations