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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical altercations and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks that indicate the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     affili
    -0.93
     enriched
    -0.87
    yip
    -0.82
     extinct
    -0.80
     microbiome
    -0.80
     niche
    -0.79
     pse
    -0.79
     welcome
    -0.78
     transact
    -0.77
     inherited
    -0.75
    POSITIVE LOGITS
     Afterwards
    1.72
     Eventually
    1.70
     Later
    1.63
     Then
    1.61
     Moments
    1.51
     Seconds
    1.49
     Shortly
    1.46
     Luckily
    1.44
     Immediately
    1.44
     When
    1.43
    Act Density 0.283%

    No Known Activations