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

    Neuronpedia

    INDEX
    Explanations

    prepositions and their frequency in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azeera
    -0.74
    hops
    -0.71
    oglu
    -0.69
    glomer
    -0.69
     etc
    -0.68
    aters
    -0.67
    opt
    -0.67
    cellent
    -0.65
    chell
    -0.65
    urther
    -0.65
    POSITIVE LOGITS
     behalf
    0.74
     sanity
    0.70
     theirs
    0.68
     letting
    0.66
     his
    0.63
     subdu
    0.62
     himself
    0.61
     declaring
    0.60
     Scarlet
    0.59
     defeating
    0.59
    Act Density 0.504%

    No Known Activations