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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating signs or indicators of various phenomena or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     שוליים
    -0.90
    ERICK
    -0.78
    enderror
    -0.77
    PerformLayout
    -0.71
    \"");
    -0.71
    athlon
    -0.71
    felder
    -0.71
    rália
    -0.67
    expandindo
    -0.66
    beitung
    -0.66
    POSITIVE LOGITS
     Signs
    1.86
     signs
    1.81
    Signs
    1.77
     SIGNS
    1.72
     Sign
    1.71
     sign
    1.67
     SIGN
    1.64
    signs
    1.60
    sign
    1.60
    Sign
    1.57
    Act Density 0.079%

    No Known Activations