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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "gri" or related word forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ncy
    -0.18
    nout
    -0.16
    rou
    -0.15
    ritch
    -0.15
    cop
    -0.15
    mission
    -0.15
    λον
    -0.14
    rowse
    -0.14
    nd
    -0.14
    roud
    -0.14
    POSITIVE LOGITS
    i
    0.27
    pped
    0.21
    bose
    0.20
    iid
    0.20
    ps
    0.19
    ãĥ¥
    0.19
    pen
    0.19
    osite
    0.19
    ego
    0.19
    pping
    0.18
    Act Density 0.052%

    No Known Activations