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

    Neuronpedia

    INDEX
    Explanations

    references to limbs or limb-related terminology

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    >{@
    -0.93
    MessageOf
    -0.86
     nakalista
    -0.85
     houſe
    -0.83
     consommateurs
    -0.82
    AsUp
    -0.81
     Nebel
    -0.80
     Monfieur
    -0.79
     Cæsar
    -0.79
    بوابة
    -0.78
    POSITIVE LOGITS
     limb
    1.67
    limb
    1.57
     limbs
    1.52
     Limb
    1.39
     Lim
    1.05
    Lim
    0.98
     LIM
    0.96
    LIM
    0.84
     arm
    0.82
     limp
    0.80
    Act Density 0.005%

    No Known Activations