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

    Neuronpedia

    INDEX
    Explanations

    negative character traits and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itor
    -0.15
     Dank
    -0.15
    alth
    -0.14
     Rider
    -0.14
    bis
    -0.14
    Ïį
    -0.14
    imentary
    -0.14
     prox
    -0.14
     Rope
    -0.13
    333
    -0.13
    POSITIVE LOGITS
     trouble
    0.24
     troub
    0.20
     trait
    0.20
     lun
    0.20
     optim
    0.19
     vag
    0.19
     prima
    0.19
     impost
    0.19
     psych
    0.19
    nik
    0.18
    Act Density 0.437%

    No Known Activations