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

    Neuronpedia

    INDEX
    Explanations

    references to interpersonal relationships and emotional reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oni
    -0.17
    ienes
    -0.15
    loat
    -0.14
    persona
    -0.14
    oned
    -0.14
    rito
    -0.14
    iej
    -0.13
    bone
    -0.13
    zza
    -0.13
    {}{↵
    -0.13
    POSITIVE LOGITS
    andler
    0.16
    ced
    0.15
    ãģ¾ãģ¾
    0.15
    croft
    0.14
    ding
    0.14
    abela
    0.14
     JOB
    0.14
     extern
    0.14
    pid
    0.14
    862
    0.14
    Act Density 0.332%

    No Known Activations