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

    Neuronpedia

    INDEX
    Explanations

    prepositions and their frequency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ly
    -0.87
     with
    -0.59
    mente
    -0.58
    jména
    -0.55
    s
    -0.54
    they
    -0.53
     of
    -0.52
     in
    -0.52
     they
    -0.52
     gangen
    -0.51
    POSITIVE LOGITS
     be
    1.36
     ensure
    1.12
     avoid
    1.09
    plevel
    1.01
     accommodate
    0.98
     achieve
    0.98
     satisfy
    0.95
    pless
    0.95
     celebrate
    0.95
     prevent
    0.94
    Act Density 0.562%

    No Known Activations