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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "where"

    oai_token-act-pair · gpt-3.5-turbo

    the word "where" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Beetle
    -0.64
     Doctrine
    -0.64
    ³³³³³³³³
    -0.60
    ouf
    -0.59
    rolet
    -0.58
     franc
    -0.57
     Salam
    -0.57
    thal
    -0.57
     Hook
    -0.57
    apult
    -0.57
    POSITIVE LOGITS
    upon
    1.47
    abouts
    1.28
    soever
    1.20
    fore
    1.16
    with
    0.73
    earch
    0.73
    rency
    0.71
    ¿½
    0.70
    inis
    0.67
     they
    0.66
    Act Density 0.062%

    No Known Activations