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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or tasks that can be done

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hum
    -0.17
    ima
    -0.17
    .emf
    -0.15
    iu
    -0.15
     ench
    -0.15
    еÑĤе
    -0.14
    UNUSED
    -0.14
    iment
    -0.14
     meaning
    -0.13
     Hum
    -0.13
    POSITIVE LOGITS
     happening
    0.24
     happens
    0.23
     happen
    0.23
     Happ
    0.22
     happened
    0.21
    ToDo
    0.18
     aconte
    0.17
     happ
    0.17
     done
    0.16
     accomplished
    0.16
    Act Density 0.130%

    No Known Activations