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

    Neuronpedia

    INDEX
    Explanations

    references to television shows and their characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Yao
    -0.18
     Dao
    -0.17
     Kos
    -0.16
     Erdogan
    -0.15
     Panda
    -0.15
     panda
    -0.15
     Sok
    -0.15
     TOK
    -0.15
     Yuri
    -0.15
     kos
    -0.14
    POSITIVE LOGITS
     Psycho
    0.37
     Norman
    0.35
     Bates
    0.35
    Psy
    0.33
     Hitch
    0.32
    Norm
    0.30
     Norm
    0.30
     Marion
    0.27
     Perkins
    0.27
     psycho
    0.26
    Act Density 0.006%

    No Known Activations