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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and emotional struggles, particularly in the context of relationships and family

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     läßt
    -1.16
     daß
    -1.15
     muß
    -1.13
     !!!!!
    -0.98
     !!!!
    -0.96
     skall
    -0.94
    luß
    -0.93
     !!!
    -0.91
     mußte
    -0.87
     !!!!!!
    -0.85
    POSITIVE LOGITS
     ⁠
    1.22
    ⁠
    1.02
    ⏤
    0.87
    ––
    0.86
     alongside
    0.81
    Alongside
    0.75
    Trusted
    0.75
    ⸺
    0.74
     throughout
    0.74
     thanks
    0.72
    Act Density 0.478%

    No Known Activations