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

    Neuronpedia

    INDEX
    Explanations

    phrases related to military and technological topics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of press or media organizations and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eternity
    -0.81
    ãģĻ
    -0.76
    $.
    -0.76
    é¾įå
    -0.74
    rather
    -0.67
    76561
    -0.65
    ãģı
    -0.65
    ãģĦ
    -0.64
     sidx
    -0.62
     oneself
    -0.61
    POSITIVE LOGITS
     consists
    0.89
     has
    0.86
     meanwhile
    0.82
     welcomed
    0.79
     reacted
    0.79
     reacts
    0.78
     grew
    0.77
     teamed
    0.76
     responded
    0.75
     debuted
    0.74
    Act Density 1.175%

    No Known Activations