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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progression and patterns in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    působ
    -0.15
    lectual
    -0.14
    ãĥ¼ãĥª
    -0.14
    ält
    -0.14
    tails
    -0.14
    æĮ¯
    -0.14
    eless
    -0.14
    xed
    -0.14
    åŃ¸æł¡
    -0.14
    ика
    -0.14
    POSITIVE LOGITS
     evolution
    0.19
     nas
    0.17
     kin
    0.17
     evolutionary
    0.15
    792
    0.15
    lan
    0.14
     Evolution
    0.14
    eres
    0.14
    opal
    0.14
    uristic
    0.14
    Act Density 0.118%

    No Known Activations