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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating movement and direction

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "from" indicating origin or source

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TEXT
    -0.79
    Sys
    -0.78
    rition
    -0.76
    inion
    -0.76
    quote
    -0.76
    merce
    -0.71
    ascript
    -0.70
    ratulations
    -0.70
    stros
    -0.70
    stakes
    -0.69
    POSITIVE LOGITS
     afar
    1.35
     whence
    1.30
     thence
    1.15
     abroad
    0.83
     inside
    0.82
     beneath
    0.78
     atop
    0.77
     across
    0.73
     somewhere
    0.73
     underneath
    0.72
    Act Density 0.163%

    No Known Activations