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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Ô
    -0.98
    Actor
    -0.83
    Hop
    -0.76
    çĶ°
    -0.74
    Father
    -0.74
    м
    -0.73
    ODY
    -0.71
    ICS
    -0.71
    ELF
    -0.70
    ãĥŁ
    -0.70
    POSITIVE LOGITS
    illard
    0.72
    cius
    0.64
    elt
    0.63
    ettel
    0.62
    orsi
    0.62
     Raider
    0.62
     induced
    0.62
     Proposition
    0.62
     Meadows
    0.61
     Radiant
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.