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

    Neuronpedia

    INDEX
    Explanations

    the phrase "This" in various contexts throughout the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idis
    -0.15
    athom
    -0.15
    ulfilled
    -0.15
    idon
    -0.15
    ouce
    -0.15
    ycastle
    -0.14
    icap
    -0.14
    iddi
    -0.14
    ë
    -0.14
    eniable
    -0.13
    POSITIVE LOGITS
     is
    0.21
     done
    0.16
     again
    0.16
     can
    0.16
     may
    0.16
     ob
    0.15
     will
    0.15
     align
    0.15
     should
    0.15
    /go
    0.15
    Act Density 0.124%

    No Known Activations