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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "working" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lessly
    -0.20
    .imag
    -0.14
    ioneer
    -0.14
    宿
    -0.14
    voy
    -0.14
    fat
    -0.14
    аза
    -0.14
    ÑģÑĤин
    -0.14
    ingly
    -0.14
    Prov
    -0.14
    POSITIVE LOGITS
    -class
    0.23
    -Class
    0.21
     working
    0.20
     Working
    0.20
    Working
    0.17
    -working
    0.17
     stiff
    0.16
    éļİ
    0.16
    ROUP
    0.15
     knowledge
    0.15
    Act Density 0.022%

    No Known Activations