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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate sequential actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĦ
    -0.15
    RU
    -0.15
    ses
    -0.15
    sel
    -0.15
    .IsAny
    -0.14
    dl
    -0.14
    portun
    -0.14
    γÏīν
    -0.14
    erm
    -0.14
    anness
    -0.13
    POSITIVE LOGITS
    -up
    0.27
     closely
    0.25
     suit
    0.25
     receipt
    0.21
     completion
    0.20
    -Up
    0.18
     upon
    0.17
     instructions
    0.16
     along
    0.16
     Suit
    0.16
    Act Density 0.018%

    No Known Activations