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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emotional or relational dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    κει
    -0.17
    lesh
    -0.16
    ylie
    -0.15
     Sır
    -0.15
    riba
    -0.15
    SSL
    -0.15
    orm
    -0.15
    veau
    -0.14
     Ulus
    -0.14
    ampo
    -0.14
    POSITIVE LOGITS
     falls
    0.22
     falling
    0.21
     Falling
    0.21
     Falls
    0.21
     fell
    0.21
     asleep
    0.19
     Fallen
    0.19
     trap
    0.19
     fall
    0.18
    falls
    0.18
    Act Density 0.029%

    No Known Activations