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

    Neuronpedia

    INDEX
    Explanations

    steps or instructions for a technical process, likely related to electronics or mechanics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Carcinogenicity
    -0.55
    quité
    -0.51
     Baillargeon
    -0.50
    marle
    -0.49
    ectoria
    -0.49
    tonode
    -0.49
     Bourgoin
    -0.48
     Leiter
    -0.47
    atars
    -0.47
     Feier
    -0.46
    POSITIVE LOGITS
     pop
    1.35
     Pop
    1.29
     pops
    1.26
     popping
    1.23
     POP
    1.22
     intersper
    1.19
     popped
    1.18
     encomp
    1.17
    Pop
    1.17
     emphat
    1.17
    Act Density 0.073%

    No Known Activations