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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote locations or contexts involving "in" and "at."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asar
    -0.17
    hole
    -0.16
    ine
    -0.15
     Dol
    -0.15
    ari
    -0.15
     del
    -0.14
    aved
    -0.14
     Lee
    -0.14
    .ib
    -0.14
    holes
    -0.14
    POSITIVE LOGITS
    ayah
    0.14
     wre
    0.14
    orias
    0.14
     sling
    0.14
    iero
    0.14
    quire
    0.14
    ëĶ°
    0.14
    ermo
    0.14
     tük
    0.14
    ruk
    0.14
    Act Density 0.011%

    No Known Activations