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

    Neuronpedia

    INDEX
    Explanations

    narratives discussing personal and historical struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     видÑĥ
    -0.14
    elter
    -0.14
    .Selenium
    -0.14
     disturb
    -0.14
    cuts
    -0.14
    ildren
    -0.13
    ÄĻp
    -0.13
    iales
    -0.13
    Æ°Æ¡ng
    -0.13
    åı¸
    -0.13
    POSITIVE LOGITS
     how
    0.26
     experiences
    0.24
     lives
    0.24
     life
    0.23
    å¦Ĥä½ķ
    0.23
     events
    0.21
     struggle
    0.20
     exploits
    0.19
     interactions
    0.18
     struggles
    0.18
    Act Density 0.187%

    No Known Activations