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

    Neuronpedia

    INDEX
    Explanations

    themes related to community and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĭãĥ¼
    -0.14
    ترÙĨت
    -0.14
    олиÑĤ
    -0.14
    verty
    -0.14
     annonces
    -0.13
    pte
    -0.12
    ระ
    -0.12
     каж
    -0.12
    ollipop
    -0.12
     nghiêm
    -0.12
    POSITIVE LOGITS
     created
    0.30
     Created
    0.25
     flawed
    0.25
     imperfect
    0.24
     made
    0.24
     unique
    0.23
     human
    0.23
    created
    0.23
     creations
    0.22
     capable
    0.22
    Act Density 0.179%

    No Known Activations