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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe emotional states and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Both
    -0.17
     Both
    -0.17
    osy
    -0.15
     both
    -0.15
    ree
    -0.14
     BOTH
    -0.14
    alsa
    -0.14
     beide
    -0.14
    å¼ı
    -0.14
    both
    -0.14
    POSITIVE LOGITS
     etc
    0.23
    etc
    0.21
    tering
    0.15
    whatever
    0.14
    .IContainer
    0.14
    /etc
    0.14
     whatever
    0.14
    ãģªãģ©
    0.14
     all
    0.14
    INLINE
    0.14
    Act Density 0.129%

    No Known Activations