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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a causal relationship or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.59
    contentLoaded
    -0.50
     kasarigan
    -0.49
    ----</
    -0.49
    ByExample
    -0.41
    setVerticalGroup
    -0.41
    .*")]
    -0.38
     propOrder
    -0.38
    IVEREF
    -0.38
     pasada
    -0.36
    POSITIVE LOGITS
     accompanies
    0.68
     accompany
    0.67
     accompanying
    0.67
     concomitant
    0.64
    随之
    0.56
    companying
    0.56
     kèm
    0.56
     accompanied
    0.50
     сопрово
    0.50
    に伴
    0.50
    Act Density 0.489%

    No Known Activations