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

    Neuronpedia

    INDEX
    Explanations

    sources or attributions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "via."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Difference
    -0.69
    erest
    -0.66
    stood
    -0.64
    APTER
    -0.62
    apest
    -0.56
     Gleaming
    -0.56
     lett
    -0.55
    Honest
    -0.55
     serious
    -0.54
    venants
    -0.54
    POSITIVE LOGITS
     via
    3.29
    via
    2.01
     Via
    1.90
    Via
    1.82
     through
    1.50
     courtesy
    1.23
     indirectly
    1.18
    through
    1.11
     thru
    1.11
     directly
    1.05
    Act Density 0.023%

    No Known Activations