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

    Neuronpedia

    INDEX
    Explanations

    words indicating possession or attributes related to individuals or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Schro
    -0.14
    /DTD
    -0.14
    Ľå»º
    -0.14
     loa
    -0.14
    ække
    -0.14
     McGregor
    -0.14
    arcy
    -0.14
    OffsetTable
    -0.13
    anko
    -0.13
    HING
    -0.13
    POSITIVE LOGITS
     snap
    0.15
    lename
    0.15
    435
    0.15
    Edition
    0.15
    ovat
    0.14
     liberties
    0.14
    snap
    0.13
    :host
    0.13
    ncoder
    0.13
    .vn
    0.13
    Act Density 0.042%

    No Known Activations