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

    Neuronpedia

    INDEX
    Explanations

    references to academic publications and their volumes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ✨:
    -0.79
     bezeichneter
    -0.78
    ]';
    -0.73
    ++
    -0.68
    >';
    -0.68
    eriksaan
    -0.67
    `;
    -0.62
    >&
    -0.57
     Penrose
    -0.57
     dejo
    -0.57
    POSITIVE LOGITS
     Vol
    1.79
     vol
    1.78
    vol
    1.70
    Vol
    1.66
     VOL
    1.58
    VOL
    1.48
     Vols
    1.36
     vols
    1.15
     Völ
    1.07
    vols
    1.05
    Act Density 0.034%

    No Known Activations