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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships and familial connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    URITY
    -0.16
     Záp
    -0.15
    assis
    -0.15
    deniz
    -0.15
    ("")]↵
    -0.15
     EXEMPLARY
    -0.14
    jist
    -0.14
    uos
    -0.14
    appa
    -0.14
     mne
    -0.14
    POSITIVE LOGITS
     loved
    0.73
     Loved
    0.62
     relative
    0.43
     relatives
    0.41
    relative
    0.40
     Relative
    0.36
     Relatives
    0.34
    Relative
    0.34
     loves
    0.32
     family
    0.31
    Act Density 0.174%

    No Known Activations