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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" indicating actions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ink
    -0.17
    ud
    -0.16
    ception
    -0.15
    se
    -0.15
    ning
    -0.15
     sport
    -0.15
    u
    -0.15
    ingle
    -0.15
    an
    -0.14
    asti
    -0.14
    POSITIVE LOGITS
    .onView
    0.16
    ácil
    0.16
    athom
    0.15
    isposable
    0.15
    IFY
    0.15
    iasm
    0.14
    eless
    0.14
    .XR
    0.14
    ToBounds
    0.14
    iator
    0.14
    Act Density 0.031%

    No Known Activations