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

    Neuronpedia

    INDEX
    Explanations

    phrases that express excessive feelings or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eler
    -0.16
    abis
    -0.16
    erb
    -0.15
    onymous
    -0.14
    onde
    -0.14
    adir
    -0.14
    ãĥ¼ãĥª
    -0.13
    ãģ§ãģĤ
    -0.13
    -prepend
    -0.13
    oint
    -0.13
    POSITIVE LOGITS
     TOO
    0.21
     Too
    0.21
    too
    0.20
    Too
    0.20
     too
    0.19
    sse
    0.17
    -too
    0.17
    太
    0.16
    -than
    0.15
    leDb
    0.15
    Act Density 0.106%

    No Known Activations