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

    Neuronpedia

    INDEX
    Explanations

    important nouns and named entities related to speech or communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sd
    -0.17
     Baghd
    -0.15
    ungs
    -0.15
    656
    -0.14
    ovo
    -0.14
    weg
    -0.14
     CONSEQUENTIAL
    -0.14
    nes
    -0.14
    uld
    -0.13
    639
    -0.13
    POSITIVE LOGITS
    ISE
    0.17
    ardown
    0.15
    eparator
    0.14
    agrid
    0.14
    ôle
    0.14
    empor
    0.14
    annah
    0.14
     Thatcher
    0.14
     Strict
    0.13
     stag
    0.13
    Act Density 0.001%

    No Known Activations