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

    Neuronpedia

    INDEX
    Explanations

    emotional responses and impacts of various situations on individuals and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     WithEvents
    -0.17
    hte
    -0.14
    ÏħÏĩ
    -0.14
    SessionFactory
    -0.14
    otas
    -0.14
    ullet
    -0.14
    yro
    -0.14
     поÑĤен
    -0.13
    poi
    -0.13
    yle
    -0.13
    POSITIVE LOGITS
     harm
    0.21
     havoc
    0.20
     problems
    0.19
     Problems
    0.18
     stir
    0.17
    iesel
    0.17
     damage
    0.16
    etsk
    0.16
     Harm
    0.16
    problems
    0.16
    Act Density 0.055%

    No Known Activations