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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "After"

    oai_token-act-pair · gpt-3.5-turbo

    transitions or continuations in narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    JV
    -0.72
    NRS
    -0.70
    DN
    -0.70
    Especially
    -0.69
    女
    -0.69
     constitu
    -0.68
    IZE
    -0.67
    uci
    -0.66
    çī
    -0.62
    NR
    -0.62
    POSITIVE LOGITS
    wards
    1.44
    noon
    1.38
    ward
    1.37
    math
    1.24
    words
    1.06
     awhile
    1.02
    word
    1.01
     careful
    0.98
     graduating
    0.96
     inspecting
    0.96
    Act Density 0.070%

    No Known Activations