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

    Neuronpedia

    INDEX
    Explanations

    terms related to bending or deformation, particularly in a physical or mechanical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -0.81
    /*
    -0.73
     numberWith
    -0.68
     Seeder
    -0.63
    OrBuilder
    -0.63
     imedi
    -0.61
    Vanjske
    -0.60
    savefig
    -0.59
     Haddad
    -0.59
    spaced
    -0.59
    POSITIVE LOGITS
     bending
    1.07
     Bend
    0.99
     bend
    0.98
    Bend
    0.97
     bends
    0.95
    bend
    0.95
    twisted
    0.95
     Bending
    0.94
     bent
    0.91
     Twisted
    0.89
    Act Density 0.360%

    No Known Activations