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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating a specific point in time or location

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "as" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iris
    -0.67
    irk
    -0.62
    asis
    -0.62
    let
    -0.62
    leness
    -0.61
    ingo
    -0.61
    ivals
    -0.61
    oras
    -0.59
    ilitarian
    -0.58
    stals
    -0.58
    POSITIVE LOGITS
     reported
    0.95
    ylum
    0.90
    bestos
    0.87
     cited
    0.87
    ynchron
    0.85
     recounted
    0.85
     usual
    0.85
     part
    0.83
     quoted
    0.83
     instructed
    0.79
    Act Density 0.123%

    No Known Activations