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

    Neuronpedia

    INDEX
    Explanations

    instances of the substring "tr" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tr
    -0.18
    tring
    -0.16
    edly
    -0.16
    HEMA
    -0.15
    arkin
    -0.15
    callable
    -0.15
    igne
    -0.14
     Appropri
    -0.14
    esp
    -0.14
     comm
    -0.14
    POSITIVE LOGITS
    uck
    0.25
    unk
    0.21
    ail
    0.20
    acked
    0.20
    actor
    0.19
    ails
    0.18
    ains
    0.18
    ucks
    0.18
    ough
    0.17
    ims
    0.17
    Act Density 0.020%

    No Known Activations