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

    Neuronpedia

    INDEX
    Explanations

    sentences that denote causation or effect, particularly through the use of the verbs "make" and "makes."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bahía
    -0.48
     Ibid
    -0.45
    logError
    -0.45
    tvrt
    -0.44
     borbo
    -0.43
    webElementXpaths
    -0.42
     torchvision
    -0.42
     pimienta
    -0.41
     civils
    -0.41
    Witam
    -0.41
    POSITIVE LOGITS
    make
    1.22
     make
    1.16
    Make
    1.11
     Make
    1.11
    makes
    1.09
    made
    1.08
    Making
    1.06
    Made
    1.03
    MAKE
    1.03
    making
    1.02
    Act Density 0.180%

    No Known Activations