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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the word "Home."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isco
    -0.19
    .Router
    -0.17
    umper
    -0.16
    icle
    -0.15
    rio
    -0.15
     loosen
    -0.14
    /loose
    -0.14
    ýt
    -0.14
    ISCO
    -0.14
     sluts
    -0.14
    POSITIVE LOGITS
    ington
    0.18
    /Home
    0.17
     Op
    0.15
    INGTON
    0.15
    781
    0.15
    582
    0.15
    coming
    0.15
    lined
    0.15
    æĸ¼
    0.14
    erule
    0.14
    Act Density 0.011%

    No Known Activations