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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases related to locations or connections between entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    sbm
    -0.70
    andowski
    -0.70
    pring
    -0.65
    yg
    -0.65
    zin
    -0.64
    aryn
    -0.64
    tri
    -0.62
    pair
    -0.62
    DragonMagazine
    -0.62
     congr
    -0.62
    POSITIVE LOGITS
     its
    0.91
     theirs
    0.87
    pload
    0.77
     their
    0.71
     Cuba
    0.70
     rubble
    0.68
     orbit
    0.67
     Havana
    0.65
     Himself
    0.65
     itself
    0.64
    Act Density 0.270%

    No Known Activations