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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue or quotes within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hastings
    -0.16
    aged
    -0.16
    sters
    -0.16
    ula
    -0.15
     jar
    -0.15
    ota
    -0.15
    edium
    -0.15
    aget
    -0.15
    stered
    -0.15
    ola
    -0.15
    POSITIVE LOGITS
    gett
    0.15
    .obs
    0.15
    sen
    0.14
     Obr
    0.14
    .dtd
    0.14
     Carousel
    0.14
    ktop
    0.14
     Jas
    0.14
     ext
    0.14
     Serif
    0.14
    Act Density 0.261%

    No Known Activations