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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reflection and contemplation

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions that indicate ongoing situations or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uta
    -0.80
    ICES
    -0.73
    hered
    -0.72
    HCR
    -0.71
    anz
    -0.70
    GY
    -0.70
    ses
    -0.69
    umbn
    -0.69
    case
    -0.69
    acas
    -0.68
    POSITIVE LOGITS
     rightfully
    1.29
     moreover
    1.18
     rightly
    1.15
     furthermore
    1.12
     therefore
    1.10
     consequently
    1.09
     luckily
    1.06
     hence
    1.05
     hopefully
    1.00
     frankly
    0.99
    Act Density 0.230%

    No Known Activations