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

    Neuronpedia

    INDEX
    Explanations

    references to dyes used in research or experimentation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    <h3>
    -0.65
    <h6>
    -0.59
    Unmanaged
    -0.59
    mura
    -0.58
    typescript
    -0.58
    </s>
    -0.57
     Ə
    -0.57
     Clemente
    -0.57
     Ávila
    -0.57
     knock
    -0.56
    POSITIVE LOGITS
     Dye
    1.56
     dye
    1.55
     dyes
    1.48
    Dye
    1.41
    dye
    1.34
     dyed
    1.00
     dyeing
    0.93
    Cyfeiriadau
    0.92
    0.86
    MLLoader
    0.84
    Act Density 0.002%

    No Known Activations