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

    Neuronpedia

    INDEX
    Explanations

    locations and events related to news articles

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to serious events and crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cale
    -0.83
    âĹ¼
    -0.75
    pring
    -0.71
    MpServer
    -0.71
    conservancy
    -0.71
    iate
    -0.69
    ippi
    -0.67
    boro
    -0.67
    NetMessage
    -0.67
    ãģĦ
    -0.67
    POSITIVE LOGITS
     shuts
    0.91
     survives
    0.89
     sparks
    0.84
     Allows
    0.81
     slams
    0.80
     connects
    0.79
    uses
    0.77
     destroys
    0.76
     develops
    0.76
     opens
    0.76
    Act Density 0.423%

    No Known Activations