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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ocative
    -0.75
    Hart
    -0.72
    Chel
    -0.70
    Smith
    -0.68
    HQ
    -0.65
    Reviewed
    -0.65
    LESS
    -0.65
    IDES
    -0.63
    tones
    -0.62
    ESS
    -0.62
    POSITIVE LOGITS
    unity
    0.70
     trave
    0.69
    agame
    0.68
     Bahá
    0.66
     Roku
    0.66
    emies
    0.65
     Obi
    0.64
     Mana
    0.64
     estab
    0.63
    anwhile
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.