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

    Neuronpedia

    INDEX
    Explanations

    the phrase "to" in various contexts indicating intent or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zych
    -0.17
    abaj
    -0.16
    -hearted
    -0.15
    cimal
    -0.14
    opher
    -0.14
     dán
    -0.14
    eut
    -0.13
    eba
    -0.13
    úb
    -0.13
    nap
    -0.13
    POSITIVE LOGITS
     approach
    0.20
     approaching
    0.17
     approached
    0.16
    achen
    0.16
    anco
    0.15
    ustomer
    0.15
    .IContainer
    0.14
     Approach
    0.14
    ise
    0.14
     Gilles
    0.14
    Act Density 0.022%

    No Known Activations