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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to different types of work or labor, especially in specialized contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     latter
    -0.36
    âĢIJ
    -0.20
    EGIN
    -0.18
    agua
    -0.18
    phans
    -0.17
    deaux
    -0.17
    UGIN
    -0.16
    ses
    -0.15
    anguage
    -0.15
    /her
    -0.15
    POSITIVE LOGITS
    /-
    0.46
    odore
    0.27
    gether
    0.26
    atre
    0.24
    adays
    0.20
    -turned
    0.20
    ÑįÑĤомÑĥ
    0.20
    ir
    0.19
    -old
    0.19
    ern
    0.18
    Act Density 1.064%

    No Known Activations