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

    Neuronpedia

    INDEX
    Explanations

    web addresses

    oai_token-act-pair · gpt-3.5-turbo

    frequent occurrences of the character sequence "." (periods)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     caucuses
    -0.56
    terday
    -0.56
    lihood
    -0.56
     Haram
    -0.55
     Skydragon
    -0.54
     Feast
    -0.54
     posture
    -0.54
     videot
    -0.54
     Roots
    -0.53
     Predator
    -0.53
    POSITIVE LOGITS
    uk
    1.14
    nz
    1.07
    rency
    0.87
    kr
    0.85
    merce
    0.83
    jp
    0.82
    fecture
    0.80
    ucl
    0.74
    za
    0.74
    legraph
    0.74
    Act Density 0.056%

    No Known Activations