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

    Neuronpedia

    INDEX
    Explanations

    words related to historical locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "os" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¬
    -0.67
     grounds
    -0.66
    OWS
    -0.65
    taker
    -0.65
    OUT
    -0.64
    ASED
    -0.63
    ufact
    -0.62
    ãĥ©ãĥ³
    -0.61
     Cox
    -0.61
    è¦ļéĨĴ
    -0.59
    POSITIVE LOGITS
    hiba
    1.43
    ophical
    1.11
    omething
    1.08
    cano
    1.08
    ophy
    1.06
    heet
    1.06
    opher
    1.05
    hei
    1.03
    mith
    1.02
    aurus
    1.00
    Act Density 0.026%

    No Known Activations