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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases related to legal or procedural actions and principles

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to agreements, processes, and established relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idine
    -0.60
    ZI
    -0.59
    dden
    -0.57
    Redd
    -0.55
    racuse
    -0.55
     juven
    -0.54
     Burg
    -0.54
     lett
    -0.53
     Tray
    -0.53
    dx
    -0.52
    POSITIVE LOGITS
     includes
    0.82
     include
    0.76
     expired
    0.74
     culminated
    0.72
     consisted
    0.72
     came
    0.67
     included
    0.67
     haun
    0.65
     expires
    0.65
    ģĸ
    0.64
    Act Density 0.310%

    No Known Activations