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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by a noun phrase

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to different types of items or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensen
    -0.63
     redesign
    -0.61
    etermination
    -0.60
    âĢ
    -0.59
     lapt
    -0.58
    matter
    -0.57
     haul
    -0.57
     condem
    -0.56
     clipboard
    -0.55
     aside
    -0.55
    POSITIVE LOGITS
     these
    0.82
    these
    0.80
    those
    0.75
     those
    0.71
    them
    0.71
    ses
    0.70
    Adams
    0.67
     ours
    0.67
    arb
    0.65
     them
    0.64
    Act Density 0.102%

    No Known Activations