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

    Neuronpedia

    INDEX
    Explanations

    sentiments related to confusion and emotional responses in interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Them
    -0.16
    igit
    -0.16
    them
    -0.15
    Them
    -0.15
     them
    -0.14
    hausen
    -0.14
    ç¥
    -0.14
    uong
    -0.14
    amic
    -0.14
    ure
    -0.14
    POSITIVE LOGITS
     me
    0.47
     us
    0.46
     themselves
    0.31
     ours
    0.31
    æĪij
    0.30
     нами
    0.30
    ç»ĻæĪij
    0.30
     мне
    0.28
     my
    0.27
     mine
    0.26
    Act Density 0.789%

    No Known Activations