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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possession or relationships involving "of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     is
    -0.84
     was
    -0.69
    an
    -0.59
     témoins
    -0.58
    ion
    -0.56
     attentes
    -0.55
    su
    -0.54
     does
    -0.53
     itself
    -0.51
    er
    -0.51
    POSITIVE LOGITS
     '\\;'
    1.02
    ſelves
    0.95
     cherchés
    0.92
     }}$}
    0.92
    adaptiveStyles
    0.90
    ."</
    0.87
    "])
    0.86
    )";
    0.85
    ✨:
    0.83
     CURIAM
    0.83
    Act Density 0.628%

    No Known Activations