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

    Neuronpedia

    INDEX
    Explanations

    phrases related to opinions or conclusions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a cause or condition related to something previously mentioned

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bangl
    -0.61
    imental
    -0.60
     Arbit
    -0.58
     Chu
    -0.58
     Thib
    -0.58
    tz
    -0.57
    igs
    -0.57
     Farming
    -0.57
    erk
    -0.56
    dit
    -0.56
    POSITIVE LOGITS
     consequently
    0.94
     accordingly
    0.85
     doubtless
    0.81
     certainly
    0.81
     promptly
    0.80
     thereafter
    0.78
     nowhere
    0.78
     culminated
    0.75
     definitely
    0.75
     rightfully
    0.74
    Act Density 0.265%

    No Known Activations