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

    Neuronpedia

    INDEX
    Explanations

    the word "thus" or variations of it, indicating conclusions or implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    readcr
    -0.17
    rosse
    -0.16
    EFA
    -0.15
    olec
    -0.15
    thon
    -0.15
    eer
    -0.14
    chai
    -0.14
    iece
    -0.14
    opt
    -0.14
    hai
    -0.13
    POSITIVE LOGITS
    forth
    0.30
    ly
    0.28
    rd
    0.25
    far
    0.21
    soever
    0.19
    iasm
    0.18
    infeld
    0.17
    ../../../
    0.17
     far
    0.16
    elve
    0.16
    Act Density 0.018%

    No Known Activations