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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or events taking place

    oai_token-act-pair · gpt-3.5-turbo

    sentences related to significant events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plet
    -0.80
    itage
    -0.76
    uly
    -0.74
    cade
    -0.73
     credential
    -0.72
    bledon
    -0.72
     microbiome
    -0.71
    ire
    -0.70
     pros
    -0.69
    ital
    -0.69
    POSITIVE LOGITS
     Meanwhile
    1.46
     Eventually
    1.34
     Whilst
    1.33
     Luckily
    1.33
     Afterwards
    1.32
     However
    1.32
     Along
    1.32
     Unfortunately
    1.28
     Fortunately
    1.26
     Knowing
    1.24
    Act Density 0.269%

    No Known Activations