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

    Neuronpedia

    INDEX
    Explanations

    phrases specifically indicating singularity or uniqueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     either
    -0.16
    ãĥIJãĤ¤
    -0.16
    IRCLE
    -0.15
    ior
    -0.15
     Keystone
    -0.15
     Enc
    -0.15
     tu
    -0.14
    edu
    -0.14
     Tu
    -0.14
    าà¸Ķ
    -0.14
    POSITIVE LOGITS
    uyá»ģn
    0.16
    ippi
    0.15
    atee
    0.14
    erdale
    0.14
    ingham
    0.14
    awks
    0.14
    ocha
    0.14
    ละ
    0.13
    ÑĢаÑħ
    0.13
    ichi
    0.13
    Act Density 0.038%

    No Known Activations