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

    Neuronpedia

    INDEX
    Explanations

    correlations and relationships between different numerical variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    marc
    -0.45
    goi
    -0.43
    ]=='
    -0.43
    comprom
    -0.43
    <<<<<<<<<<<<
    -0.42
    feder
    -0.42
    apr
    -0.41
    **
    -0.41
    SSON
    -0.41
     talaga
    -0.39
    POSITIVE LOGITS
     negative
    2.46
     Negative
    2.28
    negative
    2.21
    Negative
    2.20
     positive
    2.07
     NEGATIVE
    2.04
     Positive
    2.00
     (-
    1.96
    positive
    1.89
    Positive
    1.87
    Act Density 2.620%

    No Known Activations