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

    Neuronpedia

    INDEX
    Explanations

    words related to comparison and evaluation, such as "but" and "especially"

    oai_token-act-pair · gpt-3.5-turbo

    references to user interface elements and interactions with technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iphate
    -0.61
    etta
    -0.56
    ism
    -0.53
    eering
    -0.52
    ujah
    -0.52
    omics
    -0.51
    orship
    -0.51
     Organization
    -0.50
    ona
    -0.50
     lawfully
    -0.50
    POSITIVE LOGITS
     luckily
    0.91
     thankfully
    0.86
     fortunately
    0.84
     unfortunately
    0.82
     alas
    0.81
     suffice
    0.80
     hopefully
    0.76
     sadly
    0.75
     hey
    0.64
     nevertheless
    0.63
    Act Density 0.765%

    No Known Activations