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

    Neuronpedia

    INDEX
    Explanations

    expressions related to personal preferences and tastes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.45
    锈钢
    -0.45
    pakah
    -0.45
    bootstrapcdn
    -0.44
    曖昧さ回避
    -0.44
     Meksiku
    -0.44
     differentiate
    -0.43
     allAfrica
    -0.43
    tanleria
    -0.41
    ∭
    -0.41
    POSITIVE LOGITS
    preferences
    0.60
     liking
    0.58
     preferences
    0.58
    Loves
    0.56
     gustaba
    0.55
     lover
    0.55
     gustan
    0.55
     preference
    0.54
     Preferences
    0.54
    loves
    0.54
    Act Density 0.298%

    No Known Activations