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

    Neuronpedia

    INDEX
    Explanations

    terms related to bending and shapes of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /*
    -0.89
    Datuak
    -0.80
    aarrggbb
    -0.78
     TestBed
    -0.75
    withIdentifier
    -0.69
     Seeder
    -0.69
    BeginContext
    -0.68
    baomidou
    -0.67
    __':
    -0.67
    ceiro
    -0.67
    POSITIVE LOGITS
     bending
    0.94
     Bending
    0.85
     bent
    0.80
     bend
    0.80
     Fold
    0.79
     dobra
    0.79
    bend
    0.78
     Bend
    0.77
    twisted
    0.76
    折
    0.75
    Act Density 0.356%

    No Known Activations