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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "shown."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     _('
    -0.72
    Datuak
    -0.66
    ddy
    -0.64
    dy
    -0.61
    DotNetBar
    -0.59
    dede
    -0.59
     ''),
    -0.59
    (&:
    -0.59
    ivez
    -0.58
    dys
    -0.57
    POSITIVE LOGITS
     AssemblyCulture
    1.05
    findpost
    0.78
    EDEFAULT
    0.73
    ICATED
    0.72
    clusal
    0.72
     propOrder
    0.72
    minecraftforge
    0.69
    speakers
    0.69
    antMatchers
    0.69
     Prit
    0.69
    Act Density 0.015%

    No Known Activations