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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships and community connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asso
    -0.15
    onas
    -0.15
    ulton
    -0.15
    ertino
    -0.15
    ounter
    -0.15
     Rough
    -0.14
    izzo
    -0.14
    icers
    -0.14
    ilver
    -0.14
    ogui
    -0.14
    POSITIVE LOGITS
     loved
    0.19
     friends
    0.16
     yourself
    0.16
     someone
    0.16
     friend
    0.16
     Loved
    0.15
    _TBL
    0.15
     family
    0.15
     Boss
    0.14
     Male
    0.14
    Act Density 0.076%

    No Known Activations