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

    Neuronpedia

    INDEX
    Explanations

    words related to alcoholic beverages

    oai_token-act-pair · gpt-3.5-turbo

    words related to unique or distinctive characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    coming
    -0.79
    itably
    -0.75
    anger
    -0.75
    dfx
    -0.74
    owment
    -0.72
    ough
    -0.70
    angers
    -0.70
    baugh
    -0.70
    ãĥ¡
    -0.69
    itable
    -0.68
    POSITIVE LOGITS
    ique
    0.82
    eers
    0.81
    nil
    0.76
    eer
    0.75
    urs
    0.73
     Vie
    0.69
    vre
    0.68
     Franc
    0.68
    ira
    0.67
    lder
    0.65
    Act Density 0.031%

    No Known Activations