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

    Neuronpedia

    INDEX
    Explanations

    numerical ratios and their relationships in analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amu
    -0.16
     поба
    -0.15
    imb
    -0.15
    plier
    -0.14
     Hosp
    -0.14
    urator
    -0.14
    325
    -0.13
    beros
    -0.13
    ourcing
    -0.13
    tempt
    -0.13
    POSITIVE LOGITS
     researched
    0.18
     researching
    0.16
    ãĥ¼ãĥ
    0.15
     depend
    0.15
     Territories
    0.15
    singular
    0.15
    /dc
    0.14
    ascade
    0.14
    Intensity
    0.14
     intensely
    0.14
    Act Density 0.067%

    No Known Activations