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

    Neuronpedia

    INDEX
    Explanations

    terms related to crafting and cracks in materials

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    VersionUID
    -0.82
     Helios
    -0.81
     Berner
    -0.80
    }>{
    -0.79
     Helix
    -0.77
    //
    -0.77
    textcolor
    -0.74
    ه‌ای
    -0.74
     Colón
    -0.74
    metheus
    -0.73
    POSITIVE LOGITS
    cra
    1.41
    Cra
    1.34
     Cra
    1.29
     crack
    1.21
    cracked
    1.16
     Cracker
    1.14
     CRA
    1.13
     cracked
    1.13
     Crafts
    1.12
     cra
    1.09
    Act Density 0.020%

    No Known Activations