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

    Neuronpedia

    INDEX
    Explanations

    phrases that begin with "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    as to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enfans
    -0.49
     gonzález
    -0.49
    nexpected
    -0.49
     sánchez
    -0.48
     rempliss
    -0.48
    Activ
    -0.47
     instalada
    -0.46
     Houſe
    -0.46
    timedia
    -0.46
    Residents
    -0.46
    POSITIVE LOGITS
     concerning
    0.56
    to
    0.55
     to
    0.54
    adaptiveStyles
    0.52
     UPON
    0.52
     bezüglich
    0.52
     جهت
    0.51
     regarding
    0.50
     pertaining
    0.49
    xsi
    0.49
    Act Density 0.013%

    No Known Activations