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

    Neuronpedia

    INDEX
    Explanations

    specific prepositions indicating movement or direction, particularly 'in'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "going in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =]
    -0.64
    TED
    -0.58
    STER
    -0.58
    %"
    -0.54
    DN
    -0.54
    PIN
    -0.53
    CLASSIFIED
    -0.53
    peak
    -0.52
    IAS
    -0.52
    ANGE
    -0.51
    POSITIVE LOGITS
    humane
    1.07
    ordinate
    1.00
    escap
    1.00
    wards
    1.00
     unison
    1.00
    animate
    0.99
    vert
    0.97
    sole
    0.96
    between
    0.93
    efficiency
    0.93
    Act Density 0.222%

    No Known Activations