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

    Neuronpedia

    INDEX
    Explanations

    references to the sun and solar phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    עת
    -0.67
    cshtml
    -0.67
     ]];
    -0.63
    regist
    -0.62
    ▼
    -0.60
    {'
    -0.60
    emble
    -0.59
    ↵↵↵↵↵
    -0.58
    āla
    -0.58
    </thead>
    -0.57
    POSITIVE LOGITS
     Sun
    2.54
     sun
    2.49
    Sun
    2.44
     SUN
    2.38
    sun
    2.37
    SUN
    2.22
     suns
    1.95
     Suns
    1.86
     soleil
    1.63
     sunshine
    1.62
    Act Density 0.036%

    No Known Activations