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

    Neuronpedia

    INDEX
    Explanations

    terms related to limitations or constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     بيها
    -0.80
    windigkeit
    -0.80
    enumi
    -0.78
    ovsk
    -0.75
    tableFuture
    -0.75
     Ayers
    -0.74
    objs
    -0.73
    pearance
    -0.70
     Armies
    -0.69
    Appearances
    -0.69
    POSITIVE LOGITS
     restriction
    1.58
     restrictions
    1.58
     restrict
    1.51
     restricted
    1.48
     Restrictions
    1.48
     Restriction
    1.43
     restricts
    1.40
     restricting
    1.38
     Restricted
    1.37
    restriction
    1.33
    Act Density 0.096%

    No Known Activations