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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases related to demand, consequences, and change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    favor
    -0.14
     Favor
    -0.14
    outers
    -0.14
    oram
    -0.13
    peek
    -0.13
    haven
    -0.13
     lie
    -0.13
    stem
    -0.13
    odash
    -0.13
     æĽ
    -0.13
    POSITIVE LOGITS
     expect
    0.19
     sticking
    0.19
     NAT
    0.18
     natural
    0.18
    Expect
    0.18
    èĩªçĦ¶
    0.17
     expectation
    0.17
    ä¸įåı¯
    0.17
     Natural
    0.17
     Expect
    0.17
    Act Density 0.012%

    No Known Activations