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

    Neuronpedia

    INDEX
    Explanations

    references to scientific studies and their results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -1.11
    GEBURTSDATUM
    -1.00
    المناصب
    -0.95
     Савезне
    -0.90
    bootstrapcdn
    -0.87
    "},
    -0.86
    .)}
    -0.85
    ']=$
    -0.83
    ³/
    -0.83
    ']")
    -0.83
    POSITIVE LOGITS
    ,
    0.67
    .
    0.67
    ;
    0.55
    CrossRef
    0.51
    enderror
    0.44
    )
    0.43
     poule
    0.42
     paš
    0.40
     kväll
    0.39
     popolari
    0.38
    Act Density 0.244%

    No Known Activations