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

    Neuronpedia

    INDEX
    Explanations

    descriptors related to weight and fineness in materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hazi
    -0.15
    γά
    -0.15
    ipse
    -0.15
    êt
    -0.15
    ãĥ¼ãĥģ
    -0.15
    ÑģÑĸм
    -0.14
    idth
    -0.14
    stadt
    -0.14
    anova
    -0.14
    ouro
    -0.14
    POSITIVE LOGITS
    /light
    0.26
     (<
    0.21
    light
    0.18
    (<
    0.17
    /tiny
    0.16
     light
    0.15
    (light
    0.15
    /loose
    0.15
    .light
    0.15
    -light
    0.15
    Act Density 0.093%

    No Known Activations