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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to."

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

    to + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    -0.47
    iettivo
    -0.35
    ://
    -0.34
     Hartley
    -0.32
     demais
    -0.32
     The
    -0.31
    rejected
    -0.31
    ,
    -0.31
     Zah
    -0.30
     Gere
    -0.30
    POSITIVE LOGITS
    LookAnd
    0.78
    awtextra
    0.75
    MENAFN
    0.60
    +#+#
    0.60
    DataSnapshot
    0.60
     propOrder
    0.60
    0.60
    UserScript
    0.59
     surla
    0.58
    PYX
    0.57
    Act Density 0.063%

    No Known Activations