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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases indicating alternate perspectives or contrasting ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    सन
    -0.14
    åĩĮ
    -0.14
    xe
    -0.14
    ÏĥÏĦα
    -0.14
    обÑĭ
    -0.13
    dra
    -0.13
    .properties
    -0.13
    çļĦäºĭ
    -0.13
     quo
    -0.13
    reesome
    -0.13
    POSITIVE LOGITS
     flip
    0.35
     contrary
    0.31
     plus
    0.29
    flip
    0.28
     bright
    0.28
     surface
    0.27
     upside
    0.26
     brighter
    0.26
     whole
    0.25
    surface
    0.24
    Act Density 0.039%

    No Known Activations