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

    Neuronpedia

    INDEX
    Explanations

    phrases related to agreement and negotiation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramer
    -0.17
    oster
    -0.16
    quet
    -0.15
     Calder
    -0.15
    imitive
    -0.15
    rouw
    -0.14
    atha
    -0.14
    itom
    -0.14
    Ïĥι
    -0.14
     kern
    -0.14
    POSITIVE LOGITS
    istle
    0.15
    onis
    0.15
    .poll
    0.14
    utors
    0.14
    358
    0.14
    AGO
    0.14
     isc
    0.14
    ourn
    0.14
    GetInstance
    0.14
     scroll
    0.13
    Act Density 0.373%

    No Known Activations