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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating location or direction

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     awa
    -0.75
    orge
    -0.73
    encer
    -0.73
    hemy
    -0.72
    allo
    -0.69
    issance
    -0.66
    ugu
    -0.66
    onym
    -0.65
    enda
    -0.64
    llor
    -0.64
    POSITIVE LOGITS
     regards
    0.77
     order
    0.76
     hopes
    0.76
     anticipation
    0.76
     whichever
    0.72
    versions
    0.71
    king
    0.71
     lieu
    0.70
     accordance
    0.70
     densely
    0.70
    Act Density 0.496%

    No Known Activations