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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating relationships or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Havel
    -0.68
    fuj
    -0.66
    </td>
    -0.66
     Sixt
    -0.65
    ']){
    -0.65
    7
    -0.64
     Kitts
    -0.64
    カワ
    -0.62
     censi
    -0.61
     νό
    -0.61
    POSITIVE LOGITS
    Σε
    0.85
     σε
    0.84
     Shand
    0.82
    sqcup
    0.79
    ruptcy
    0.79
     saites
    0.78
     saltwater
    0.74
     Erskine
    0.73
     écran
    0.72
    Hochspringen
    0.72
    Act Density 0.125%

    No Known Activations