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

    Neuronpedia

    INDEX
    Explanations

    terms related to resistance or opposing forces in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ings
    -0.21
    ystone
    -0.19
    inged
    -0.17
    INGS
    -0.16
    tra
    -0.16
     ê°ĻìĿ´
    -0.15
    ãĥ£
    -0.15
    xin
    -0.15
    obi
    -0.15
    ith
    -0.15
    POSITIVE LOGITS
    ive
    0.25
    ances
    0.20
     against
    0.20
    ively
    0.20
     Against
    0.19
    /res
    0.18
    ANCE
    0.18
    ivec
    0.17
    à¸Ĺาà¸Ļ
    0.17
    ivity
    0.17
    Act Density 0.019%

    No Known Activations