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

    Neuronpedia

    INDEX
    Explanations

    names and titles related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    specific names or identifiers related to individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    footed
    -0.75
     lawy
    -0.64
     thumb
    -0.62
    Reviewer
    -0.61
     Flavoring
    -0.61
     thumbs
    -0.61
     academ
    -0.60
    avorite
    -0.59
    irlf
    -0.58
    nesday
    -0.57
    POSITIVE LOGITS
    ette
    0.73
    enne
    0.72
    atis
    0.69
    opa
    0.69
    ela
    0.68
    oes
    0.67
    Angelo
    0.67
     Wynne
    0.67
    idge
    0.66
     Reck
    0.66
    Act Density 0.054%

    No Known Activations