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

    Neuronpedia

    INDEX
    Explanations

    conjunctions connecting different clauses or phrases in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esk
    -0.17
    olt
    -0.15
     sonst
    -0.15
    pch
    -0.14
    åŀĭ
    -0.14
    Scoped
    -0.14
     Preconditions
    -0.14
    Backing
    -0.14
    áºŃn
    -0.13
    iggins
    -0.13
    POSITIVE LOGITS
     began
    0.23
     soon
    0.20
     became
    0.19
    soon
    0.18
     camb
    0.17
    then
    0.16
     eventually
    0.16
    vo
    0.15
     shortly
    0.15
     Duffy
    0.15
    Act Density 0.216%

    No Known Activations