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

    Neuronpedia

    INDEX
    Explanations

    dates expressed in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    references to dates and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quartered
    -0.75
    etheless
    -0.73
    Reloaded
    -0.65
    isode
    -0.64
    ascular
    -0.64
    reditary
    -0.63
    rontal
    -0.62
    itri
    -0.59
     Gleaming
    -0.59
    Topics
    -0.58
    POSITIVE LOGITS
    lang
    0.72
     Quan
    0.71
    ħĭ
    0.68
    fi
    0.64
     reader
    0.63
    si
    0.63
    é¾
    0.62
    ciating
    0.60
     tremend
    0.59
     Lauder
    0.58
    Act Density 0.790%

    No Known Activations