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

    Neuronpedia

    INDEX
    Explanations

    words associated with new experiences and changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulla
    -0.15
    ookie
    -0.15
    reu
    -0.15
    rown
    -0.14
    umph
    -0.13
    essler
    -0.13
    tees
    -0.13
     еÑģÑĤÑĮ
    -0.13
    \widgets
    -0.13
     wed
    -0.13
    POSITIVE LOGITS
    ĶåĽŀ
    0.16
    imals
    0.15
    ynam
    0.15
    arov
    0.15
    ÄŁan
    0.14
    λί
    0.14
    اط
    0.14
    aton
    0.14
    ude
    0.14
    ação
    0.14
    Act Density 0.061%

    No Known Activations