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

    Neuronpedia

    INDEX
    Explanations

    words related to math, specifically angles and bisectors

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bian
    -0.07
    åľĪ
    -0.06
     invert
    -0.06
     Romero
    -0.06
     inverted
    -0.06
    ij
    -0.06
    eno
    -0.06
     Marty
    -0.06
     inversion
    -0.06
     negative
    -0.06
    POSITIVE LOGITS
     bis
    0.08
    allis
    0.07
     divides
    0.07
    -angle
    0.07
     Divider
    0.07
     splits
    0.07
     splitting
    0.06
    -divider
    0.06
    åĪĨ
    0.06
    redirect
    0.06
    Act Density 0.128%

    No Known Activations