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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    },{"
    -0.74
    hare
    -0.67
    hawk
    -0.66
     tallest
    -0.65
    tis
    -0.61
    allery
    -0.60
    otics
    -0.59
    plex
    -0.59
    iatrics
    -0.58
    bush
    -0.58
    POSITIVE LOGITS
     Reload
    0.79
     Lod
    0.70
    vern
    0.69
    culus
    0.68
    ppo
    0.67
    ÄŁ
    0.65
     Papa
    0.64
     Kens
    0.63
     Provision
    0.62
     Cue
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.