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

    Neuronpedia

    INDEX
    Explanations

    references to specific items or concepts, such as "egg," "BST 1," "mort," "redd 1," and "Cly 1."

    oai_token-act-pair · gpt-3.5-turbo

    references to eggs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mediated
    -0.69
     Marshal
    -0.68
     supervised
    -0.67
    anship
    -0.67
     polic
    -0.65
     manned
    -0.65
     anchored
    -0.64
     Noir
    -0.64
     patrols
    -0.63
    avior
    -0.62
    POSITIVE LOGITS
    egg
    4.42
     BST
    1.10
    mort
    1.04
    Redd
    0.86
    unic
    0.82
    clusions
    0.81
     redd
    0.81
    agher
    0.79
    cloud
    0.78
    fred
    0.76
    Act Density 0.049%

    No Known Activations