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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    erest
    -0.73
    ys
    -0.71
    lesh
    -0.70
    BLIC
    -0.70
    elf
    -0.69
    ANY
    -0.67
    neum
    -0.66
    alloc
    -0.65
    anch
    -0.65
    NetMessage
    -0.64
    POSITIVE LOGITS
     swear
    0.70
    ="#
    0.68
    -+-+
    0.65
    atin
    0.64
     Wag
    0.64
    inders
    0.62
    #$
    0.62
     Starg
    0.62
    =#
    0.61
     Hugo
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.