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

    Neuronpedia

    INDEX
    Explanations

    the word "under" or variations of it, indicating context related to conditions or states beneath a certain level

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥªãĤ«
    -0.15
    rch
    -0.14
    icipant
    -0.14
    runner
    -0.14
    imuth
    -0.14
    yclic
    -0.14
    orgot
    -0.14
    egend
    -0.13
    ilter
    -0.13
    OLL
    -0.13
    POSITIVE LOGITS
    neath
    0.34
    lined
    0.28
    lining
    0.27
    lying
    0.27
     ausp
    0.26
    lie
    0.25
     circumstances
    0.25
    pin
    0.25
    sea
    0.24
    foot
    0.24
    Act Density 0.061%

    No Known Activations