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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "through."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agoon
    -0.17
     Morrow
    -0.15
    mana
    -0.15
    ÑĪкÑĥ
    -0.15
    matchCondition
    -0.14
    urity
    -0.14
     phong
    -0.14
    orrect
    -0.13
    mons
    -0.13
     Toe
    -0.13
    POSITIVE LOGITS
    umann
    0.19
    nemonic
    0.16
    -out
    0.15
    INDER
    0.15
    ough
    0.14
    lrt
    0.14
    ylene
    0.14
    705
    0.14
    ecycle
    0.13
    atatype
    0.13
    Act Density 0.080%

    No Known Activations