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

    Neuronpedia

    INDEX
    Explanations

    statements related to conditionality and implications in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    новништво
    -0.64
     nzuri
    -0.62
    UserScript
    -0.61
    
    -0.59
     sane
    -0.58
    AsUp
    -0.57
     enak
    -0.56
    Typical
    -0.55
    новниш
    -0.55
    nice
    -0.54
    POSITIVE LOGITS
     incomplete
    1.03
     unreliable
    0.90
     limited
    0.88
     inadequate
    0.85
     imperfect
    0.85
     unstable
    0.83
    incomplete
    0.82
     insufficient
    0.82
     Incomplete
    0.80
     inadequ
    0.79
    Act Density 0.651%

    No Known Activations