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

    Neuronpedia

    INDEX
    Explanations

    referential phrases indicating location or origin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    emerged from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.69
     myſelf
    -0.65
     ſtand
    -0.64
    ſſel
    -0.59
    wiſe
    -0.59
     faſt
    -0.57
    AddTagHelper
    -0.56
     leſs
    -0.54
     diſt
    -0.54
     IndexPath
    -0.54
    POSITIVE LOGITS
     uscire
    0.52
     emerged
    0.46
     emerging
    0.42
    走出
    0.41
     emerge
    0.40
     Inside
    0.40
     Exit
    0.37
    Inside
    0.36
     exit
    0.36
    Emerging
    0.35
    Act Density 0.012%

    No Known Activations