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

    Neuronpedia

    INDEX
    Explanations

    phrases that express intention or desire to take action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    earch
    -0.15
    eld
    -0.14
     intersection
    -0.14
    character
    -0.14
     meis
    -0.14
     Petty
    -0.14
    omb
    -0.13
    onces
    -0.13
     noreferrer
    -0.13
     brokerage
    -0.13
    POSITIVE LOGITS
    åIJ§
    0.16
    ÑĢаÑĤно
    0.15
    ornado
    0.15
     skoro
    0.15
    /cpp
    0.15
    åłĤ
    0.15
    .Guna
    0.15
    arda
    0.14
    284
    0.14
    eni
    0.14
    Act Density 0.078%

    No Known Activations