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

    Neuronpedia

    INDEX
    Explanations

    text related to location or spatial positions

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and adverbs indicating spatial or positional relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     alloc
    -0.69
     transitions
    -0.61
     disson
    -0.60
     suffix
    -0.59
     VIDEOS
    -0.58
    Previous
    -0.58
     assumes
    -0.57
    Newsletter
    -0.57
    Sequ
    -0.57
     fuels
    -0.57
    POSITIVE LOGITS
    fed
    0.98
    orthy
    0.90
    enced
    0.88
    raged
    0.80
    alysed
    0.78
    occupied
    0.78
    cerned
    0.73
     ready
    0.72
    acebook
    0.70
    ped
    0.70
    Act Density 0.169%

    No Known Activations