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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases indicating location or position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     underground
    -0.15
    rch
    -0.15
    sik
    -0.15
    ãĥªãĤ«
    -0.15
    yclic
    -0.15
     Underground
    -0.14
    orgot
    -0.14
    anje
    -0.14
    upertino
    -0.14
    WEBPACK
    -0.13
    POSITIVE LOGITS
    neath
    0.32
    lined
    0.29
    lining
    0.28
     ausp
    0.26
    sea
    0.26
    lying
    0.26
    whel
    0.25
    pin
    0.25
    lie
    0.24
     circumstances
    0.24
    Act Density 0.065%

    No Known Activations