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

    Neuronpedia

    INDEX
    Explanations

    phrases related to impactful events, condolences, and community support

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    furt
    -0.79
     targeting
    -0.79
    setup
    -0.78
     vetting
    -0.77
     escalate
    -0.75
     pretext
    -0.75
     coord
    -0.74
    blocking
    -0.74
    coord
    -0.74
    plan
    -0.73
    POSITIVE LOGITS
     memorial
    1.29
    RIP
    1.28
     remembrance
    1.26
     remem
    1.26
     Remem
    1.21
     anniversary
    1.21
     memories
    1.20
     remembered
    1.16
     legacy
    1.16
     mourn
    1.14
    Act Density 3.372%

    No Known Activations