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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement or direction

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    oir
    -0.77
    Ultra
    -0.74
    quickShipAvailable
    -0.74
    ogi
    -0.68
    gone
    -0.68
    OLOGY
    -0.67
    zu
    -0.67
    083
    -0.67
    INT
    -0.66
    inn
    -0.66
    POSITIVE LOGITS
     interchange
    0.90
     throughout
    0.89
     depending
    0.80
    ilaterally
    0.80
     alike
    0.78
     altern
    0.78
     movements
    0.76
     respectively
    0.76
    )=(
    0.74
     across
    0.74
    Act Density 0.053%

    No Known Activations