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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating locations or contexts within a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aldi
    -0.18
    htable
    -0.16
     Years
    -0.15
    nis
    -0.15
    thing
    -0.14
    ulace
    -0.14
    notated
    -0.14
     ÑĥÑģ
    -0.14
    ors
    -0.14
    ned
    -0.14
    POSITIVE LOGITS
     case
    0.20
     stead
    0.20
    ital
    0.18
    -place
    0.17
    fty
    0.17
     future
    0.17
    italize
    0.17
     theory
    0.17
    ited
    0.16
     reality
    0.16
    Act Density 0.185%

    No Known Activations