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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and technical terms of various subjects

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names of individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.52
    anwhile
    -0.46
    raltar
    -0.43
    atchewan
    -0.42
    083
    -0.41
    ividual
    -0.40
    udic
    -0.40
    shapeshifter
    -0.39
    èĢħ
    -0.39
    ãĥł
    -0.37
    POSITIVE LOGITS
    iosyn
    0.56
    natureconservancy
    0.48
     hous
    0.43
    terness
    0.42
     overc
    0.41
    ilyn
    0.40
    irez
    0.40
     artif
    0.38
    oton
    0.38
    NetMessage
    0.38
    Act Density 2.735%

    No Known Activations