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

    Neuronpedia

    INDEX
    Explanations

    descriptors of physical appearances and characteristics in characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    еÑĢин
    -0.15
    ähr
    -0.15
    Prostit
    -0.14
    erot
    -0.14
    ContentLoaded
    -0.14
     turist
    -0.14
    ÏģÏİ
    -0.14
    èĪĮ
    -0.13
    éŀ
    -0.13
    /root
    -0.13
    POSITIVE LOGITS
     tall
    0.34
     bald
    0.27
     pale
    0.26
     taller
    0.26
     fat
    0.25
     thin
    0.25
     stock
    0.25
     wir
    0.25
     ga
    0.24
     middle
    0.24
    Act Density 0.471%

    No Known Activations