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

    Neuronpedia

    INDEX
    Explanations

    descriptors of materials and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Höhe
    -0.32
     relocation
    -0.32
    ⓧ
    -0.31
     очки
    -0.30
     spare
    -0.30
     платфор
    -0.30
    folger
    -0.30
    betical
    -0.29
     compensation
    -0.29
    řevě
    -0.29
    POSITIVE LOGITS
     texture
    1.00
     softness
    0.93
     hardness
    0.88
     textures
    0.83
     softer
    0.82
     textura
    0.81
     Texture
    0.81
     Hardness
    0.78
     textured
    0.77
    texture
    0.77
    Act Density 0.460%

    No Known Activations