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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing relationships and characteristics of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anything
    -0.15
    enes
    -0.14
    ishment
    -0.14
    dration
    -0.14
    agnostics
    -0.14
    simp
    -0.14
     selves
    -0.13
    åĢĭ人
    -0.13
     лÑİбой
    -0.13
    bsp
    -0.13
    POSITIVE LOGITS
     whom
    0.24
     connections
    0.21
     ties
    0.20
     interests
    0.20
     plans
    0.19
     dreams
    0.19
     ambitions
    0.19
     aspirations
    0.18
     Down
    0.18
     roots
    0.16
    Act Density 0.288%

    No Known Activations