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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by specific targets or subjects

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    edin
    -0.81
    oslav
    -0.77
    entimes
    -0.77
    nick
    -0.75
    pert
    -0.74
    zona
    -0.74
    beat
    -0.74
    soever
    -0.73
    mone
    -0.69
    nikov
    -0.69
    POSITIVE LOGITS
    gery
    1.02
     inclusion
    0.99
     future
    0.98
    geries
    0.95
    bidden
    0.93
     tomorrow
    0.90
     upcoming
    0.89
     awhile
    0.85
     sale
    0.81
     resolving
    0.81
    Act Density 0.288%

    No Known Activations