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

    Neuronpedia

    INDEX
    Explanations

    sections that are formatted as citations with a colon

    oai_token-act-pair · gpt-3.5-turbo

    colons that introduce lists or details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ecided
    -0.80
     spont
    -0.74
    obbies
    -0.73
    pherd
    -0.70
    schild
    -0.69
    undai
    -0.69
    avorite
    -0.68
    eryl
    -0.67
    milo
    -0.67
     outl
    -0.66
    POSITIVE LOGITS
     ][
    0.90
    leg
    0.78
    Latest
    0.76
    memory
    0.74
     Explicit
    0.74
    lement
    0.70
     Provided
    0.70
    ::::::::
    0.69
     Retro
    0.68
     Comic
    0.67
    Act Density 0.033%

    No Known Activations