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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of threats or dangers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    enderror
    -0.82
     Bader
    -0.78
     Risiko
    -0.74
     ContentValues
    -0.74
    uinal
    -0.73
    picasso
    -0.72
    Checksum
    -0.72
    <h5>
    -0.69
    <th>
    -0.68
     suất
    -0.68
    POSITIVE LOGITS
     Threat
    1.31
    threat
    1.27
     threat
    1.27
     Threats
    1.25
    Threat
    1.22
    Threats
    1.19
     threats
    1.17
     threatened
    0.97
     threatening
    0.94
     threatens
    0.91
    Act Density 0.008%

    No Known Activations