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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    verse
    -0.15
    OrCreate
    -0.15
    lier
    -0.14
     antlr
    -0.14
    upgrade
    -0.14
    elier
    -0.14
    ussen
    -0.14
    nder
    -0.14
    ortal
    -0.13
    km
    -0.13
    POSITIVE LOGITS
     perfection
    0.28
     near
    0.27
     within
    0.26
     smith
    0.23
     Near
    0.23
     death
    0.23
    within
    0.22
     kingdom
    0.21
     maximum
    0.21
     exhaustion
    0.20
    Act Density 0.117%

    No Known Activations