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

    Neuronpedia

    INDEX
    Explanations

    terms related to agreements and offers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HandlerContext
    -0.73
     "..\..\
    -0.71
    ContentAlignment
    -0.69
    UnusedPrivate
    -0.65
    üyada
    -0.64
    Degree
    -0.58
     SEDS
    -0.58
     Chasse
    -0.57
     propOrder
    -0.57
    XmlAccessType
    -0.57
    POSITIVE LOGITS
     Ofer
    0.59
     offer
    0.58
     accept
    0.58
    Ці
    0.57
     acepta
    0.56
    Accepted
    0.56
    URIComponent
    0.55
     invite
    0.54
    invite
    0.53
    izr
    0.53
    Act Density 0.166%

    No Known Activations