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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negative sentiment or criticism

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express definitive statements or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ageing
    -0.93
     organising
    -0.87
     organised
    -0.83
     endeavour
    -0.82
     civilisation
    -0.81
    ijing
    -0.81
     organis
    -0.80
     unstoppable
    -0.78
     recognised
    -0.77
     exting
    -0.76
    POSITIVE LOGITS
     Neither
    1.05
     Regardless
    1.03
     Apparently
    1.00
     He
    1.00
     Asked
    0.96
     Either
    0.96
     Nope
    0.95
     Presumably
    0.94
     Eventually
    0.94
     Basically
    0.94
    Act Density 0.887%

    No Known Activations