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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "thus" indicating conclusion or causation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kv
    -0.15
    readcr
    -0.15
    ton
    -0.15
    ignKey
    -0.14
    uchos
    -0.14
    olec
    -0.14
    å®®
    -0.14
    thon
    -0.14
    chai
    -0.14
    izm
    -0.14
    POSITIVE LOGITS
    forth
    0.38
    ly
    0.30
    forward
    0.22
    LY
    0.20
    far
    0.19
    iasm
    0.19
    ìį¨
    0.17
    infeld
    0.16
    -called
    0.16
     far
    0.15
    Act Density 0.021%

    No Known Activations