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

    Neuronpedia

    INDEX
    Explanations

    phrases or words associated with adhering to specific rules or cultural practices

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "per" indicating processes, rules, or cultural practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARDIS
    -0.79
    ForgeModLoader
    -0.76
    姫
    -0.74
    çīĪ
    -0.73
     GOODMAN
    -0.72
     Plague
    -0.69
    MpServer
    -0.66
     Defenders
    -0.66
    ãĥīãĥ©
    -0.65
     Ic
    -0.65
    POSITIVE LOGITS
     capita
    1.19
    vas
    0.96
    ishable
    0.96
    malink
    0.94
    ceptive
    0.88
    missive
    0.88
    tains
    0.86
    ceptions
    0.84
    severe
    0.82
    missions
    0.82
    Act Density 0.029%

    No Known Activations