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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditions that trigger alerts or user notifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    conditional or contrastive statements introducing consequences or alternatives.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    孩子们
    -0.52
     Editors
    -0.48
     fathers
    -0.47
    人たち
    -0.47
    同学们
    -0.47
    rrggbb
    -0.47
    girls
    -0.46
     Managers
    -0.46
    énieurs
    -0.46
     Controllers
    -0.45
    POSITIVE LOGITS
    這位
    1.14
    这位
    1.10
    此人
    1.05
    这个人
    1.02
     person
    0.99
    那个人
    0.99
    那人
    0.98
    對方
    0.88
     pessoa
    0.84
    这人
    0.82
    Act Density 1.326%

    No Known Activations