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

    Neuronpedia

    INDEX
    Explanations

    mentions of different scenarios or scenarios in general

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.86
     bygget
    -0.75
    MessageState
    -0.75
     Sosa
    -0.74
     Mosley
    -0.73
    PMailer
    -0.72
    ostock
    -0.72
     ASE
    -0.71
     Blak
    -0.71
     StatelessWidget
    -0.68
    POSITIVE LOGITS
     scenarios
    1.52
     Scenarios
    1.50
    scenarios
    1.50
     Scenario
    1.47
     scenario
    1.41
    Scenario
    1.30
    scenario
    1.28
    Scen
    1.14
    cenario
    1.09
     Scen
    0.94
    Act Density 0.003%

    No Known Activations