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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential military actions or declarations in a geopolitical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    
    -0.85
    CloseOperation
    -0.83
     TextAppearance
    -0.79
     باخ
    -0.71
    ########.
    -0.68
    sidemargin
    -0.68
    Ligações
    -0.62
     photolibrary
    -0.61
    ⓧ
    -0.59
     lenker
    -0.59
    POSITIVE LOGITS
    PerformLayout
    0.68
     affects
    0.53
    anhão
    0.50
    affect
    0.49
     affecting
    0.49
     становника
    0.47
     affected
    0.46
     Affecting
    0.45
     AssemblyProduct
    0.45
     affect
    0.45
    Act Density 0.450%

    No Known Activations