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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases indicating direction or position

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "on"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OULD
    -0.83
    Commerce
    -0.80
    SourceFile
    -0.80
    fml
    -0.77
    Attempts
    -0.71
    Phys
    -0.69
    Includes
    -0.68
    Jose
    -0.68
    SHIP
    -0.68
    tions
    -0.67
    POSITIVE LOGITS
    etime
    0.98
     behalf
    0.97
    coming
    0.96
     occasion
    0.90
    itored
    0.90
    shore
    0.88
    lined
    0.88
    eness
    0.84
     board
    0.80
    screen
    0.80
    Act Density 0.110%

    No Known Activations