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

    Neuronpedia

    INDEX
    Explanations

    occurrences of identifying verbs and attributes related to personal backgrounds and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctrine
    -0.17
    theses
    -0.15
    olen
    -0.15
    itti
    -0.14
    ãĤĥ
    -0.14
    etre
    -0.14
    axies
    -0.14
    Ŀ
    -0.14
    ERGE
    -0.14
    ImageUrl
    -0.14
    POSITIVE LOGITS
     friends
    0.24
     a
    0.23
     part
    0.23
     from
    0.21
     older
    0.21
     an
    0.20
     related
    0.20
     younger
    0.19
     Jewish
    0.19
     gay
    0.18
    Act Density 0.464%

    No Known Activations