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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to action and activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Picker
    -0.15
    殿
    -0.14
    ment
    -0.14
     Morrow
    -0.14
    sey
    -0.14
     Hang
    -0.13
    (Op
    -0.13
    os
    -0.13
    nce
    -0.13
    ãĤĵãģ¨
    -0.13
    POSITIVE LOGITS
    ekli
    0.14
    ÑĤеÑĢн
    0.14
    795
    0.14
    aida
    0.14
    ÑĢд
    0.13
    ãĥ¬ãĥĥãĥĪ
    0.13
    panies
    0.13
    zek
    0.13
    romise
    0.13
    filt
    0.13
    Act Density 0.029%

    No Known Activations