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

    Neuronpedia

    INDEX
    Explanations

    topics or subjects of discussion

    oai_token-act-pair · gpt-3.5-turbo

    references to discussions or conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uilt
    -0.75
    undai
    -0.69
     Soldier
    -0.68
    aples
    -0.68
     landfall
    -0.66
    emale
    -0.66
    zyk
    -0.66
    served
    -0.64
    Constructed
    -0.62
    bered
    -0.62
    POSITIVE LOGITS
    cloth
    0.81
    bag
    0.80
    ij士
    0.78
    ership
    0.77
    athon
    0.76
    radio
    0.76
    bone
    0.76
     Talk
    0.75
    tion
    0.75
     about
    0.75
    Act Density 0.029%

    No Known Activations