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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating introspection or contemplation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hua
    -0.18
    ripp
    -0.16
    preload
    -0.16
    ardy
    -0.15
    isel
    -0.15
    uo
    -0.15
    uchen
    -0.15
    avenport
    -0.15
    gid
    -0.14
    emann
    -0.14
    POSITIVE LOGITS
     closely
    0.19
     eyes
    0.19
     глаза
    0.17
     Eyes
    0.15
     Eye
    0.15
     face
    0.15
     faces
    0.15
     eye
    0.15
    907
    0.15
    unde
    0.15
    Act Density 0.078%

    No Known Activations