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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases starting with "in"

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the presence of the word "in" indicating context or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irl
    -0.69
    iris
    -0.67
    guyen
    -0.65
    ATHER
    -0.65
    ultane
    -0.64
    ngth
    -0.62
    ById
    -0.62
    rical
    -0.61
    FontSize
    -0.61
    Nat
    -0.59
    POSITIVE LOGITS
     lieu
    1.17
     situations
    1.16
     hindsight
    1.11
     order
    1.09
     spite
    1.08
     regards
    1.05
     retrospect
    1.04
     terms
    1.04
    animate
    1.02
     relation
    0.98
    Act Density 0.279%

    No Known Activations