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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Whe
    -0.82
    VK
    -0.81
    NRS
    -0.77
    vel
    -0.73
    HO
    -0.72
    VL
    -0.71
    ´
    -0.70
    CH
    -0.70
    Hop
    -0.67
    rax
    -0.66
    POSITIVE LOGITS
    ĪĴ
    0.89
    racuse
    0.88
    ascript
    0.83
    avid
    0.80
    uyomi
    0.79
    agents
    0.72
    psc
    0.70
    ¥µ
    0.70
    igmatic
    0.65
    thora
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.