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

    Neuronpedia

    INDEX
    Explanations

    references to familial relationships and emotional connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itsu
    -0.15
     Záp
    -0.15
    URITY
    -0.15
    γμα
    -0.15
    appa
    -0.15
    jist
    -0.14
     EXEMPLARY
    -0.14
    deniz
    -0.14
    EDI
    -0.14
     Äija
    -0.14
    POSITIVE LOGITS
     loved
    0.73
     Loved
    0.60
     relatives
    0.54
     family
    0.52
     relative
    0.46
     friends
    0.43
     Relatives
    0.42
    family
    0.42
    relative
    0.41
     Relative
    0.38
    Act Density 0.247%

    No Known Activations